{ "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": 6.11570857094113, "learning_rate": 3.2258064516129035e-07, "loss": 0.9016, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.017879367925622, "learning_rate": 6.451612903225807e-07, "loss": 0.8444, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 5.959350974613726, "learning_rate": 9.67741935483871e-07, "loss": 0.8881, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 5.995175433987812, "learning_rate": 1.2903225806451614e-06, "loss": 0.9032, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 5.605981478437396, "learning_rate": 1.6129032258064516e-06, "loss": 0.8438, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.423231438910285, "learning_rate": 1.935483870967742e-06, "loss": 0.849, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.692475042687455, "learning_rate": 2.2580645161290324e-06, "loss": 0.8388, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.3258275232074315, "learning_rate": 2.580645161290323e-06, "loss": 0.8071, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.651316472948804, "learning_rate": 2.903225806451613e-06, "loss": 0.7983, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.33285842100927, "learning_rate": 3.225806451612903e-06, "loss": 0.7552, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.215149012511545, "learning_rate": 3.548387096774194e-06, "loss": 0.7933, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.6690637258179337, "learning_rate": 3.870967741935484e-06, "loss": 0.7541, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.899342999182006, "learning_rate": 4.193548387096774e-06, "loss": 0.7492, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.840839908573601, "learning_rate": 4.516129032258065e-06, "loss": 0.7329, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.768747249778525, "learning_rate": 4.838709677419355e-06, "loss": 0.7691, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.176632786302074, "learning_rate": 5.161290322580646e-06, "loss": 0.7266, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.986077383286959, "learning_rate": 5.483870967741935e-06, "loss": 0.7003, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.4275207724367327, "learning_rate": 5.806451612903226e-06, "loss": 0.7062, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.723034508820049, "learning_rate": 6.129032258064517e-06, "loss": 0.6764, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.5766200261036711, "learning_rate": 6.451612903225806e-06, "loss": 0.6753, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.7042036221711199, "learning_rate": 6.774193548387097e-06, "loss": 0.647, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.8371397853874671, "learning_rate": 7.096774193548388e-06, "loss": 0.6171, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.6819675316554394, "learning_rate": 7.4193548387096784e-06, "loss": 0.6297, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.4596209854008348, "learning_rate": 7.741935483870968e-06, "loss": 0.6104, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.245032136125739, "learning_rate": 8.064516129032258e-06, "loss": 0.6218, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.238432899276517, "learning_rate": 8.387096774193549e-06, "loss": 0.6309, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.223274632870922, "learning_rate": 8.70967741935484e-06, "loss": 0.626, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.9933851018405975, "learning_rate": 9.03225806451613e-06, "loss": 0.5988, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7234638760305155, "learning_rate": 9.35483870967742e-06, "loss": 0.6035, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.8983873128712949, "learning_rate": 9.67741935483871e-06, "loss": 0.5729, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 1.0695380051688386, "learning_rate": 1e-05, "loss": 0.5864, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7104549618944599, "learning_rate": 1.0322580645161291e-05, "loss": 0.5799, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6770360900139678, "learning_rate": 1.0645161290322582e-05, "loss": 0.56, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7987401626744647, "learning_rate": 1.096774193548387e-05, "loss": 0.5588, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.6487892227811946, "learning_rate": 1.1290322580645164e-05, "loss": 0.5628, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6215737296627409, "learning_rate": 1.1612903225806453e-05, "loss": 0.5558, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.6565700248398378, "learning_rate": 1.1935483870967743e-05, "loss": 0.5384, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6424752386188001, "learning_rate": 1.2258064516129034e-05, "loss": 0.5681, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.6417896228994996, "learning_rate": 1.2580645161290324e-05, "loss": 0.5574, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5507070037655016, "learning_rate": 1.2903225806451613e-05, "loss": 0.5403, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.6127792938402824, "learning_rate": 1.3225806451612903e-05, "loss": 0.5117, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6689636103375652, "learning_rate": 1.3548387096774194e-05, "loss": 0.5598, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5995333624128464, "learning_rate": 1.3870967741935486e-05, "loss": 0.5626, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5990440404797477, "learning_rate": 1.4193548387096776e-05, "loss": 0.5673, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6224715249096383, "learning_rate": 1.4516129032258066e-05, "loss": 0.5156, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5480172325628385, "learning_rate": 1.4838709677419357e-05, "loss": 0.5347, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.561553643267234, "learning_rate": 1.5161290322580646e-05, "loss": 0.5496, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5999534376908642, "learning_rate": 1.5483870967741936e-05, "loss": 0.5429, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5471092816149528, "learning_rate": 1.5806451612903226e-05, "loss": 0.541, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.583793208130797, "learning_rate": 1.6129032258064517e-05, "loss": 0.5315, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.6572375386922551, "learning_rate": 1.6451612903225807e-05, "loss": 0.5298, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.6918670993251232, "learning_rate": 1.6774193548387098e-05, "loss": 0.5346, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.4946690351312754, "learning_rate": 1.7096774193548388e-05, "loss": 0.5148, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5749104546741027, "learning_rate": 1.741935483870968e-05, "loss": 0.509, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7165151052263229, "learning_rate": 1.774193548387097e-05, "loss": 0.5281, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.5839808063758014, "learning_rate": 1.806451612903226e-05, "loss": 0.518, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6639078253106515, "learning_rate": 1.838709677419355e-05, "loss": 0.5434, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.49380498424588715, "learning_rate": 1.870967741935484e-05, "loss": 0.519, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5127252875907489, "learning_rate": 1.903225806451613e-05, "loss": 0.5316, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5746258651894421, "learning_rate": 1.935483870967742e-05, "loss": 0.5357, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5416007596892829, "learning_rate": 1.967741935483871e-05, "loss": 0.5063, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.4552759711663698, "learning_rate": 2e-05, "loss": 0.5199, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5867035710289613, "learning_rate": 2.0322580645161292e-05, "loss": 0.5182, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.5693447622305468, "learning_rate": 2.0645161290322582e-05, "loss": 0.5393, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.5482976486965496, "learning_rate": 2.0967741935483873e-05, "loss": 0.5273, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6142287576627159, "learning_rate": 2.1290322580645163e-05, "loss": 0.528, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.47985063396370276, "learning_rate": 2.161290322580645e-05, "loss": 0.5467, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.6406160062024362, "learning_rate": 2.193548387096774e-05, "loss": 0.523, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.5618806649571781, "learning_rate": 2.225806451612903e-05, "loss": 0.5217, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.5948360975022657, "learning_rate": 2.2580645161290328e-05, "loss": 0.4963, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.5302098604885254, "learning_rate": 2.2903225806451615e-05, "loss": 0.5141, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.5820973820845468, "learning_rate": 2.3225806451612906e-05, "loss": 0.5356, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.4962468741853926, "learning_rate": 2.3548387096774196e-05, "loss": 0.495, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.5441999559923716, "learning_rate": 2.3870967741935486e-05, "loss": 0.5315, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.5837602915614417, "learning_rate": 2.4193548387096777e-05, "loss": 0.496, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.4805457247420396, "learning_rate": 2.4516129032258067e-05, "loss": 0.5301, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.5151473473191932, "learning_rate": 2.4838709677419358e-05, "loss": 0.5038, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.6229999463701412, "learning_rate": 2.5161290322580648e-05, "loss": 0.5028, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.501524413620812, "learning_rate": 2.548387096774194e-05, "loss": 0.5378, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.5196675035235182, "learning_rate": 2.5806451612903226e-05, "loss": 0.5147, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.5226026596961675, "learning_rate": 2.6129032258064516e-05, "loss": 0.5014, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.5213105817688424, "learning_rate": 2.6451612903225806e-05, "loss": 0.5348, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.6354517723694093, "learning_rate": 2.6774193548387097e-05, "loss": 0.5327, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.6290337577281949, "learning_rate": 2.7096774193548387e-05, "loss": 0.509, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.6058718879743326, "learning_rate": 2.7419354838709678e-05, "loss": 0.4853, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.6875550283654691, "learning_rate": 2.774193548387097e-05, "loss": 0.5107, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.6395757037427289, "learning_rate": 2.8064516129032262e-05, "loss": 0.5161, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.4941356767364337, "learning_rate": 2.8387096774193552e-05, "loss": 0.4961, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.7237472057241352, "learning_rate": 2.8709677419354843e-05, "loss": 0.5152, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.6089571986447165, "learning_rate": 2.9032258064516133e-05, "loss": 0.5237, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.7170158497568591, "learning_rate": 2.9354838709677423e-05, "loss": 0.5175, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.6562814420831402, "learning_rate": 2.9677419354838714e-05, "loss": 0.5147, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.7092694520755276, "learning_rate": 3.0000000000000004e-05, "loss": 0.5028, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.6697282695436422, "learning_rate": 3.032258064516129e-05, "loss": 0.5126, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.7808895138801005, "learning_rate": 3.0645161290322585e-05, "loss": 0.5042, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.7604125563201629, "learning_rate": 3.096774193548387e-05, "loss": 0.5146, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.5489379673537841, "learning_rate": 3.1290322580645166e-05, "loss": 0.4979, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.6126881399748638, "learning_rate": 3.161290322580645e-05, "loss": 0.4733, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.5851147900824103, "learning_rate": 3.193548387096774e-05, "loss": 0.5188, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.6914738984553332, "learning_rate": 3.2258064516129034e-05, "loss": 0.5088, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.7441777900239831, "learning_rate": 3.258064516129033e-05, "loss": 0.5039, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.6116195910798806, "learning_rate": 3.2903225806451614e-05, "loss": 0.5113, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.5810609922747465, "learning_rate": 3.322580645161291e-05, "loss": 0.5035, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.6590097336210456, "learning_rate": 3.3548387096774195e-05, "loss": 0.5036, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.6849175764326898, "learning_rate": 3.387096774193549e-05, "loss": 0.5134, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.6805417216010647, "learning_rate": 3.4193548387096776e-05, "loss": 0.5084, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.6611115181906421, "learning_rate": 3.451612903225807e-05, "loss": 0.5007, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.8023834656769226, "learning_rate": 3.483870967741936e-05, "loss": 0.5063, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.7246920381239204, "learning_rate": 3.516129032258065e-05, "loss": 0.4681, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.7039376617534359, "learning_rate": 3.548387096774194e-05, "loss": 0.5093, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.6854506915968424, "learning_rate": 3.5806451612903225e-05, "loss": 0.5123, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.7796626323432642, "learning_rate": 3.612903225806452e-05, "loss": 0.5172, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.5794263010296431, "learning_rate": 3.6451612903225805e-05, "loss": 0.5, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.677328501762764, "learning_rate": 3.67741935483871e-05, "loss": 0.4892, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.8552304201565938, "learning_rate": 3.7096774193548386e-05, "loss": 0.5252, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6712697966915974, "learning_rate": 3.741935483870968e-05, "loss": 0.5176, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.8378103160336847, "learning_rate": 3.7741935483870974e-05, "loss": 0.5325, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.734897399681212, "learning_rate": 3.806451612903226e-05, "loss": 0.5057, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.606813393206946, "learning_rate": 3.8387096774193555e-05, "loss": 0.4979, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.6431240245981991, "learning_rate": 3.870967741935484e-05, "loss": 0.5069, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.6136411535270401, "learning_rate": 3.9032258064516135e-05, "loss": 0.4884, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6781382164897654, "learning_rate": 3.935483870967742e-05, "loss": 0.5106, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7067875838473494, "learning_rate": 3.9677419354838716e-05, "loss": 0.5124, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7965602546350665, "learning_rate": 4e-05, "loss": 0.5042, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.5090774506106202, "learning_rate": 3.9999920040266474e-05, "loss": 0.5206, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.6429499623748384, "learning_rate": 3.999968016170525e-05, "loss": 0.5199, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.6499432543297669, "learning_rate": 3.9999280366234394e-05, "loss": 0.523, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.5505012849792565, "learning_rate": 3.999872065705065e-05, "loss": 0.4962, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.657829471422231, "learning_rate": 3.999800103862945e-05, "loss": 0.499, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.7656630574949935, "learning_rate": 3.9997121516724834e-05, "loss": 0.4811, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.5587441459246845, "learning_rate": 3.999608209836944e-05, "loss": 0.5202, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.7044600959993237, "learning_rate": 3.999488279187443e-05, "loss": 0.4868, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.6132778491298386, "learning_rate": 3.9993523606829425e-05, "loss": 0.4779, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7358917593989293, "learning_rate": 3.9992004554102435e-05, "loss": 0.5121, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7199778199405276, "learning_rate": 3.999032564583976e-05, "loss": 0.495, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.6567863208471275, "learning_rate": 3.998848689546591e-05, "loss": 0.5094, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.8897439086817479, "learning_rate": 3.9986488317683496e-05, "loss": 0.5102, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.5925847927016852, "learning_rate": 3.9984329928473067e-05, "loss": 0.5054, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.8341615376524059, "learning_rate": 3.998201174509306e-05, "loss": 0.5184, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6371029304918592, "learning_rate": 3.997953378607961e-05, "loss": 0.4887, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.9427077060185652, "learning_rate": 3.9976896071246403e-05, "loss": 0.4809, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.568977310128506, "learning_rate": 3.997409862168454e-05, "loss": 0.4818, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.6986279050254549, "learning_rate": 3.997114145976237e-05, "loss": 0.4734, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.6235964680570768, "learning_rate": 3.9968024609125245e-05, "loss": 0.5171, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6560637493868883, "learning_rate": 3.996474809469545e-05, "loss": 0.5109, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.6694432207695539, "learning_rate": 3.996131194267189e-05, "loss": 0.4978, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.5297244213765087, "learning_rate": 3.995771618052995e-05, "loss": 0.5172, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.693723334587985, "learning_rate": 3.9953960837021256e-05, "loss": 0.5208, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.6680216958423637, "learning_rate": 3.995004594217343e-05, "loss": 0.5081, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6232300995494692, "learning_rate": 3.994597152728987e-05, "loss": 0.4838, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6057023313539115, "learning_rate": 3.994173762494947e-05, "loss": 0.4766, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6793636125838002, "learning_rate": 3.9937344269006424e-05, "loss": 0.4826, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.477387722175096, "learning_rate": 3.993279149458988e-05, "loss": 0.4822, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.6043556334415813, "learning_rate": 3.9928079338103695e-05, "loss": 0.5037, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.5376529182559615, "learning_rate": 3.992320783722616e-05, "loss": 0.4791, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7848633453498314, "learning_rate": 3.991817703090965e-05, "loss": 0.5051, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6944045748215198, "learning_rate": 3.991298695938038e-05, "loss": 0.4933, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.729801223201208, "learning_rate": 3.9907637664138e-05, "loss": 0.4978, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.5482558118023291, "learning_rate": 3.990212918795534e-05, "loss": 0.496, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.563218535452727, "learning_rate": 3.9896461574878036e-05, "loss": 0.4854, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.72047569964955, "learning_rate": 3.989063487022416e-05, "loss": 0.4736, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5869161314304585, "learning_rate": 3.9884649120583903e-05, "loss": 0.501, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5894480698074835, "learning_rate": 3.987850437381915e-05, "loss": 0.4924, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.7081621267035226, "learning_rate": 3.987220067906313e-05, "loss": 0.5195, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.7741411294021738, "learning_rate": 3.986573808672002e-05, "loss": 0.4856, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.550404730170286, "learning_rate": 3.9859116648464534e-05, "loss": 0.511, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.6925725706324481, "learning_rate": 3.985233641724152e-05, "loss": 0.486, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.5690353864931762, "learning_rate": 3.984539744726554e-05, "loss": 0.4923, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6038215391647395, "learning_rate": 3.983829979402038e-05, "loss": 0.5014, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.614157016532851, "learning_rate": 3.983104351425871e-05, "loss": 0.5074, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6201368799770738, "learning_rate": 3.982362866600154e-05, "loss": 0.5065, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.5341755629951053, "learning_rate": 3.9816055308537806e-05, "loss": 0.5138, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.5849906226885506, "learning_rate": 3.980832350242388e-05, "loss": 0.4825, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5284184807315687, "learning_rate": 3.980043330948306e-05, "loss": 0.484, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.4716684732615764, "learning_rate": 3.9792384792805124e-05, "loss": 0.4764, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5782646626281039, "learning_rate": 3.978417801674579e-05, "loss": 0.4871, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.47686122030457306, "learning_rate": 3.9775813046926244e-05, "loss": 0.4763, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5916310204471541, "learning_rate": 3.976728995023254e-05, "loss": 0.5006, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6779928817633362, "learning_rate": 3.975860879481514e-05, "loss": 0.5237, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.5932602026871289, "learning_rate": 3.974976965008833e-05, "loss": 0.4895, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5640129002680254, "learning_rate": 3.9740772586729674e-05, "loss": 0.4886, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.7116008200634307, "learning_rate": 3.973161767667946e-05, "loss": 0.531, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.48851211398015376, "learning_rate": 3.972230499314009e-05, "loss": 0.4876, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.7187836299333459, "learning_rate": 3.9712834610575545e-05, "loss": 0.4939, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.43961057034374346, "learning_rate": 3.9703206604710746e-05, "loss": 0.5034, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.6841840584746954, "learning_rate": 3.969342105253098e-05, "loss": 0.5083, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6093200129794445, "learning_rate": 3.9683478032281246e-05, "loss": 0.4939, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5269141759837189, "learning_rate": 3.967337762346568e-05, "loss": 0.5157, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.4953314223486056, "learning_rate": 3.9663119906846885e-05, "loss": 0.4675, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.46052660419443797, "learning_rate": 3.965270496444528e-05, "loss": 0.4959, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.5603759681704142, "learning_rate": 3.9642132879538465e-05, "loss": 0.4858, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5276907429426961, "learning_rate": 3.9631403736660566e-05, "loss": 0.4729, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.4668807489506098, "learning_rate": 3.962051762160151e-05, "loss": 0.4997, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.4599463109421175, "learning_rate": 3.960947462140638e-05, "loss": 0.4737, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5091833641882915, "learning_rate": 3.959827482437472e-05, "loss": 0.4947, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.4315113587478149, "learning_rate": 3.958691832005981e-05, "loss": 0.4756, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5211188877927676, "learning_rate": 3.9575405199267944e-05, "loss": 0.471, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.47122500299251496, "learning_rate": 3.956373555405774e-05, "loss": 0.4868, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.44659213926921, "learning_rate": 3.955190947773937e-05, "loss": 0.4819, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.4086463520140875, "learning_rate": 3.9539927064873824e-05, "loss": 0.4815, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.4609887707970723, "learning_rate": 3.952778841127214e-05, "loss": 0.4773, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.45968849730466865, "learning_rate": 3.95154936139947e-05, "loss": 0.4849, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.4192167123093857, "learning_rate": 3.950304277135034e-05, "loss": 0.4995, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.4215079707397134, "learning_rate": 3.94904359828957e-05, "loss": 0.4897, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.45015449230228377, "learning_rate": 3.94776733494343e-05, "loss": 0.4879, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.4115608262015417, "learning_rate": 3.9464754973015826e-05, "loss": 0.4869, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.45063015968950354, "learning_rate": 3.9451680956935275e-05, "loss": 0.5137, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.40336362607045917, "learning_rate": 3.943845140573213e-05, "loss": 0.4724, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.4173190361665674, "learning_rate": 3.942506642518952e-05, "loss": 0.5023, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.38989986929394177, "learning_rate": 3.9411526122333396e-05, "loss": 0.4852, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.4499346713397388, "learning_rate": 3.939783060543167e-05, "loss": 0.4941, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.37436251552609834, "learning_rate": 3.938397998399333e-05, "loss": 0.4904, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.42030290236207596, "learning_rate": 3.936997436876756e-05, "loss": 0.4836, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.43030731225187724, "learning_rate": 3.935581387174289e-05, "loss": 0.4919, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.4063667236402468, "learning_rate": 3.9341498606146295e-05, "loss": 0.4899, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.38291461246097364, "learning_rate": 3.932702868644224e-05, "loss": 0.5176, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.39643138106207876, "learning_rate": 3.931240422833181e-05, "loss": 0.4781, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.40056454945636705, "learning_rate": 3.9297625348751806e-05, "loss": 0.4844, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.3894221481296974, "learning_rate": 3.9282692165873744e-05, "loss": 0.4754, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.435256069748302, "learning_rate": 3.9267604799102945e-05, "loss": 0.4752, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.3650326579784634, "learning_rate": 3.9252363369077615e-05, "loss": 0.4925, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.445106441449856, "learning_rate": 3.9236967997667796e-05, "loss": 0.4807, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.40712614726673496, "learning_rate": 3.9221418807974496e-05, "loss": 0.48, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.4355849313878481, "learning_rate": 3.92057159243286e-05, "loss": 0.4692, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.42536994713434784, "learning_rate": 3.9189859472289956e-05, "loss": 0.498, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.4716838990303983, "learning_rate": 3.9173849578646324e-05, "loss": 0.467, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.41483022070244, "learning_rate": 3.9157686371412395e-05, "loss": 0.4831, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.43826746934612243, "learning_rate": 3.914136997982874e-05, "loss": 0.5085, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.4785126947859301, "learning_rate": 3.912490053436079e-05, "loss": 0.5192, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.38388626489236033, "learning_rate": 3.9108278166697805e-05, "loss": 0.4773, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.4625063088412944, "learning_rate": 3.909150300975178e-05, "loss": 0.5001, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.36973507272118006, "learning_rate": 3.907457519765642e-05, "loss": 0.49, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.4915095139017526, "learning_rate": 3.905749486576607e-05, "loss": 0.5093, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.46450244798422374, "learning_rate": 3.90402621506546e-05, "loss": 0.4909, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4706433574193074, "learning_rate": 3.902287719011435e-05, "loss": 0.4958, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.3955058077002025, "learning_rate": 3.900534012315499e-05, "loss": 0.4848, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.44210244663762716, "learning_rate": 3.8987651090002454e-05, "loss": 0.4848, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.4440125358301096, "learning_rate": 3.896981023209777e-05, "loss": 0.5093, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4602858555372031, "learning_rate": 3.8951817692095966e-05, "loss": 0.4571, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5056843985382434, "learning_rate": 3.893367361386491e-05, "loss": 0.4987, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4107361080956977, "learning_rate": 3.891537814248417e-05, "loss": 0.4741, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4566540719275544, "learning_rate": 3.889693142424384e-05, "loss": 0.4961, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.44169792713038325, "learning_rate": 3.8878333606643405e-05, "loss": 0.4846, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.48308207044361395, "learning_rate": 3.885958483839049e-05, "loss": 0.5091, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.5161197117448644, "learning_rate": 3.8840685269399786e-05, "loss": 0.4631, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.41799849657926763, "learning_rate": 3.882163505079171e-05, "loss": 0.4835, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5082394697806868, "learning_rate": 3.880243433489132e-05, "loss": 0.4898, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5142812125681944, "learning_rate": 3.878308327522702e-05, "loss": 0.4099, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.49673664887527996, "learning_rate": 3.876358202652936e-05, "loss": 0.4025, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5220890150396913, "learning_rate": 3.8743930744729835e-05, "loss": 0.4062, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6266762280849517, "learning_rate": 3.8724129586959535e-05, "loss": 0.4, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5279612586677558, "learning_rate": 3.870417871154801e-05, "loss": 0.405, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.5421886702940006, "learning_rate": 3.868407827802192e-05, "loss": 0.4012, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.44782727122151944, "learning_rate": 3.8663828447103804e-05, "loss": 0.3916, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.5340917694797911, "learning_rate": 3.8643429380710765e-05, "loss": 0.4071, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5501350006039389, "learning_rate": 3.862288124195319e-05, "loss": 0.4112, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.42800722035643013, "learning_rate": 3.8602184195133464e-05, "loss": 0.4211, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.4740813893927881, "learning_rate": 3.8581338405744604e-05, "loss": 0.392, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.45690201698773525, "learning_rate": 3.8560344040468996e-05, "loss": 0.3806, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5259662333721552, "learning_rate": 3.853920126717703e-05, "loss": 0.3846, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.4906200459564764, "learning_rate": 3.851791025492574e-05, "loss": 0.4056, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.4665383586955845, "learning_rate": 3.8496471173957515e-05, "loss": 0.3933, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.5131710475333281, "learning_rate": 3.847488419569866e-05, "loss": 0.3997, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.48388269808245427, "learning_rate": 3.8453149492758077e-05, "loss": 0.4023, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.5025124623635643, "learning_rate": 3.8431267238925886e-05, "loss": 0.4124, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5481505059900537, "learning_rate": 3.840923760917199e-05, "loss": 0.4138, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5489839042370692, "learning_rate": 3.838706077964473e-05, "loss": 0.3862, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.4858347752336517, "learning_rate": 3.836473692766944e-05, "loss": 0.3823, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.4769237794016313, "learning_rate": 3.834226623174705e-05, "loss": 0.3942, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.4940620734468955, "learning_rate": 3.831964887155264e-05, "loss": 0.4106, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.4916654066892591, "learning_rate": 3.829688502793403e-05, "loss": 0.4037, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.4385859758589964, "learning_rate": 3.827397488291029e-05, "loss": 0.3865, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.5875510740652523, "learning_rate": 3.8250918619670343e-05, "loss": 0.388, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.4428151373296128, "learning_rate": 3.822771642257145e-05, "loss": 0.4242, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.4548707819834991, "learning_rate": 3.820436847713776e-05, "loss": 0.3862, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.4582480166020062, "learning_rate": 3.8180874970058826e-05, "loss": 0.3906, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.3773345400575361, "learning_rate": 3.8157236089188103e-05, "loss": 0.3892, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.4170240832280077, "learning_rate": 3.813345202354145e-05, "loss": 0.4054, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.4333933175074532, "learning_rate": 3.810952296329563e-05, "loss": 0.4107, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.4407681045337655, "learning_rate": 3.808544909978676e-05, "loss": 0.3985, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.4469990800446498, "learning_rate": 3.806123062550882e-05, "loss": 0.377, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.4244895119779284, "learning_rate": 3.803686773411208e-05, "loss": 0.396, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.397705471621517, "learning_rate": 3.801236062040158e-05, "loss": 0.3907, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.4593649985967294, "learning_rate": 3.798770948033553e-05, "loss": 0.405, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4709949893349298, "learning_rate": 3.796291451102381e-05, "loss": 0.3874, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.4254628517904406, "learning_rate": 3.793797591072631e-05, "loss": 0.406, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.46510601039464733, "learning_rate": 3.791289387885144e-05, "loss": 0.3833, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.39198762579659613, "learning_rate": 3.788766861595443e-05, "loss": 0.3761, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5154631981975593, "learning_rate": 3.7862300323735835e-05, "loss": 0.4196, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.39250575862351983, "learning_rate": 3.783678920503983e-05, "loss": 0.4126, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.4721678001793979, "learning_rate": 3.781113546385265e-05, "loss": 0.4072, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.5003844498873893, "learning_rate": 3.7785339305300916e-05, "loss": 0.4156, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5227596938264457, "learning_rate": 3.7759400935650025e-05, "loss": 0.4059, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.3937726536702981, "learning_rate": 3.77333205623025e-05, "loss": 0.425, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.48738292459076904, "learning_rate": 3.7707098393796295e-05, "loss": 0.4017, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.38015386400443196, "learning_rate": 3.7680734639803185e-05, "loss": 0.3975, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.4975449466501347, "learning_rate": 3.765422951112704e-05, "loss": 0.4139, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.41794288009699987, "learning_rate": 3.762758321970216e-05, "loss": 0.4092, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.5079369145867065, "learning_rate": 3.7600795978591584e-05, "loss": 0.4093, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.4868205615637509, "learning_rate": 3.757386800198538e-05, "loss": 0.3784, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.5139783691420378, "learning_rate": 3.7546799505198925e-05, "loss": 0.3904, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.46758963406778165, "learning_rate": 3.7519590704671197e-05, "loss": 0.4043, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4144689421732463, "learning_rate": 3.749224181796305e-05, "loss": 0.4054, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.4842959368733628, "learning_rate": 3.746475306375545e-05, "loss": 0.3732, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.39576985624865413, "learning_rate": 3.743712466184774e-05, "loss": 0.4019, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.512187017990352, "learning_rate": 3.7409356833155885e-05, "loss": 0.3958, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.3874903202320615, "learning_rate": 3.73814497997107e-05, "loss": 0.4051, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.4916473863728325, "learning_rate": 3.7353403784656095e-05, "loss": 0.3952, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.4033801773121076, "learning_rate": 3.732521901224724e-05, "loss": 0.4023, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.42682694264077387, "learning_rate": 3.7296895707848844e-05, "loss": 0.3915, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.442311828316578, "learning_rate": 3.7268434097933275e-05, "loss": 0.3923, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.46927049320109154, "learning_rate": 3.723983441007882e-05, "loss": 0.416, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.41341137680703843, "learning_rate": 3.721109687296781e-05, "loss": 0.3964, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.48847265164874953, "learning_rate": 3.718222171638484e-05, "loss": 0.379, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.40165460572798395, "learning_rate": 3.715320917121488e-05, "loss": 0.4115, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.42730472667504, "learning_rate": 3.712405946944149e-05, "loss": 0.4144, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.40730079204441044, "learning_rate": 3.709477284414488e-05, "loss": 0.4259, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.45079996988143634, "learning_rate": 3.7065349529500136e-05, "loss": 0.3847, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.427798754335758, "learning_rate": 3.7035789760775305e-05, "loss": 0.3994, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.40071453743510865, "learning_rate": 3.70060937743295e-05, "loss": 0.4181, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.3773377881423499, "learning_rate": 3.6976261807611045e-05, "loss": 0.4099, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.4201738918157154, "learning_rate": 3.694629409915555e-05, "loss": 0.3708, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4074739939389243, "learning_rate": 3.691619088858401e-05, "loss": 0.3935, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.37513020071125, "learning_rate": 3.68859524166009e-05, "loss": 0.3905, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.4405664286616782, "learning_rate": 3.6855578924992226e-05, "loss": 0.4006, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.41605529247614353, "learning_rate": 3.6825070656623626e-05, "loss": 0.4162, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.4236081313512341, "learning_rate": 3.67944278554384e-05, "loss": 0.4125, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4188564151236892, "learning_rate": 3.676365076645557e-05, "loss": 0.4039, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4205775701564549, "learning_rate": 3.673273963576791e-05, "loss": 0.3979, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.46560524625286664, "learning_rate": 3.670169471054001e-05, "loss": 0.4184, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.43792185748893037, "learning_rate": 3.6670516239006254e-05, "loss": 0.4202, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.45793140360708273, "learning_rate": 3.663920447046888e-05, "loss": 0.4051, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.4487094779642429, "learning_rate": 3.6607759655295954e-05, "loss": 0.4054, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.4466612144737414, "learning_rate": 3.657618204491937e-05, "loss": 0.3944, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.37160275386996405, "learning_rate": 3.6544471891832875e-05, "loss": 0.3939, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.40512879985977696, "learning_rate": 3.6512629449589983e-05, "loss": 0.3959, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.414808625340567, "learning_rate": 3.6480654972802045e-05, "loss": 0.3859, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.45896480480044316, "learning_rate": 3.644854871713611e-05, "loss": 0.415, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.4465473587001149, "learning_rate": 3.6416310939312924e-05, "loss": 0.4001, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.445308729294196, "learning_rate": 3.638394189710493e-05, "loss": 0.4102, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.4253404878461227, "learning_rate": 3.635144184933412e-05, "loss": 0.4207, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.5273571022517956, "learning_rate": 3.6318811055869994e-05, "loss": 0.4152, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.4090099057326203, "learning_rate": 3.628604977762752e-05, "loss": 0.3832, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.5331917547673616, "learning_rate": 3.6253158276565004e-05, "loss": 0.4118, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.4346541883432694, "learning_rate": 3.6220136815682016e-05, "loss": 0.4117, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.4623985856115343, "learning_rate": 3.618698565901727e-05, "loss": 0.4269, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.41603986715926494, "learning_rate": 3.615370507164654e-05, "loss": 0.4051, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.4090651356400053, "learning_rate": 3.61202953196805e-05, "loss": 0.3958, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.4109635607866305, "learning_rate": 3.6086756670262654e-05, "loss": 0.3729, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.3783948737781103, "learning_rate": 3.6053089391567135e-05, "loss": 0.3879, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.4383834931683372, "learning_rate": 3.601929375279662e-05, "loss": 0.4189, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.3924525725698529, "learning_rate": 3.598537002418012e-05, "loss": 0.3868, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.3474440045294547, "learning_rate": 3.5951318476970885e-05, "loss": 0.4215, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.42441000823425773, "learning_rate": 3.591713938344416e-05, "loss": 0.4027, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.40317718576605976, "learning_rate": 3.588283301689507e-05, "loss": 0.4049, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.37589857360428336, "learning_rate": 3.5848399651636424e-05, "loss": 0.3905, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.4864490191638311, "learning_rate": 3.5813839562996473e-05, "loss": 0.4062, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.4015340178773619, "learning_rate": 3.5779153027316775e-05, "loss": 0.4011, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.4395186282956028, "learning_rate": 3.574434032194994e-05, "loss": 0.4052, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.4408840981088926, "learning_rate": 3.5709401725257436e-05, "loss": 0.4009, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.40285290416176006, "learning_rate": 3.5674337516607346e-05, "loss": 0.3883, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.4316070699882726, "learning_rate": 3.563914797637216e-05, "loss": 0.4061, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.47699738865865077, "learning_rate": 3.560383338592649e-05, "loss": 0.4137, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.45840925644226094, "learning_rate": 3.556839402764487e-05, "loss": 0.4267, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.42446149280345236, "learning_rate": 3.553283018489946e-05, "loss": 0.4168, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.4159834919310274, "learning_rate": 3.54971421420578e-05, "loss": 0.4018, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.3946523470919955, "learning_rate": 3.5461330184480524e-05, "loss": 0.4073, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.5831789621094019, "learning_rate": 3.54253945985191e-05, "loss": 0.4025, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.3969760678959443, "learning_rate": 3.5389335671513524e-05, "loss": 0.4059, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.5910424598336038, "learning_rate": 3.5353153691789986e-05, "loss": 0.4009, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.4046330836649935, "learning_rate": 3.531684894865866e-05, "loss": 0.3958, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5424389365209151, "learning_rate": 3.528042173241128e-05, "loss": 0.4105, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.5328704514673142, "learning_rate": 3.524387233431892e-05, "loss": 0.4098, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.4391810046065648, "learning_rate": 3.520720104662958e-05, "loss": 0.4063, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.37576809749653817, "learning_rate": 3.5170408162565904e-05, "loss": 0.4053, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.45940239660129967, "learning_rate": 3.513349397632281e-05, "loss": 0.3807, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.3996508543324632, "learning_rate": 3.5096458783065145e-05, "loss": 0.3906, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.4088127932857898, "learning_rate": 3.505930287892533e-05, "loss": 0.3895, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.42796602064663086, "learning_rate": 3.502202656100099e-05, "loss": 0.4129, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.4222225382478087, "learning_rate": 3.498463012735256e-05, "loss": 0.4151, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.40109176544342834, "learning_rate": 3.494711387700094e-05, "loss": 0.4041, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.41765396500236357, "learning_rate": 3.490947810992505e-05, "loss": 0.4074, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.41842291788443553, "learning_rate": 3.48717231270595e-05, "loss": 0.3878, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4419656359166386, "learning_rate": 3.483384923029211e-05, "loss": 0.4113, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.461548369056453, "learning_rate": 3.479585672246156e-05, "loss": 0.3907, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.3899417046158173, "learning_rate": 3.4757745907354924e-05, "loss": 0.4042, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.5108165652532766, "learning_rate": 3.471951708970527e-05, "loss": 0.4279, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.39171163578615825, "learning_rate": 3.468117057518921e-05, "loss": 0.3983, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.4526120745871456, "learning_rate": 3.4642706670424426e-05, "loss": 0.4096, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.3893124259750589, "learning_rate": 3.460412568296731e-05, "loss": 0.3902, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.4300410112658359, "learning_rate": 3.456542792131039e-05, "loss": 0.4073, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.36886736878175713, "learning_rate": 3.4526613694879936e-05, "loss": 0.4, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.41005221229568684, "learning_rate": 3.448768331403348e-05, "loss": 0.4022, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.4055850947347872, "learning_rate": 3.44486370900573e-05, "loss": 0.3998, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.3497518737065069, "learning_rate": 3.440947533516396e-05, "loss": 0.3897, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.39971662743379927, "learning_rate": 3.4370198362489816e-05, "loss": 0.423, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.3593893031638483, "learning_rate": 3.43308064860925e-05, "loss": 0.4185, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.38193030885471746, "learning_rate": 3.4291300020948393e-05, "loss": 0.3829, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.3736557334471836, "learning_rate": 3.425167928295015e-05, "loss": 0.3925, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.34437177138916564, "learning_rate": 3.421194458890411e-05, "loss": 0.3957, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.3831867304988897, "learning_rate": 3.4172096256527865e-05, "loss": 0.4134, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.3505811311279964, "learning_rate": 3.4132134604447595e-05, "loss": 0.389, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.4399443134507399, "learning_rate": 3.409205995219561e-05, "loss": 0.4099, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.455897072880947, "learning_rate": 3.4051872620207765e-05, "loss": 0.4017, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.4338798415451252, "learning_rate": 3.40115729298209e-05, "loss": 0.3832, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.39660293125533486, "learning_rate": 3.397116120327025e-05, "loss": 0.3995, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.41087672697766714, "learning_rate": 3.3930637763686916e-05, "loss": 0.4135, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.3932556475950534, "learning_rate": 3.389000293509524e-05, "loss": 0.392, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.3840139097226897, "learning_rate": 3.3849257042410225e-05, "loss": 0.4083, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.37131402556522136, "learning_rate": 3.380840041143494e-05, "loss": 0.4141, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.33938863479449327, "learning_rate": 3.376743336885792e-05, "loss": 0.3978, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.36922319506756285, "learning_rate": 3.372635624225055e-05, "loss": 0.3902, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.39212441338367593, "learning_rate": 3.3685169360064445e-05, "loss": 0.4115, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4164119518404608, "learning_rate": 3.3643873051628804e-05, "loss": 0.3881, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.3608210287938642, "learning_rate": 3.3602467647147814e-05, "loss": 0.4226, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.5486924367744989, "learning_rate": 3.356095347769799e-05, "loss": 0.4072, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.4195138027062732, "learning_rate": 3.351933087522552e-05, "loss": 0.4171, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.3723017276601583, "learning_rate": 3.3477600172543626e-05, "loss": 0.4249, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.40249788820488264, "learning_rate": 3.3435761703329894e-05, "loss": 0.4082, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.35070852904483585, "learning_rate": 3.3393815802123606e-05, "loss": 0.403, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.41590317654321596, "learning_rate": 3.335176280432308e-05, "loss": 0.3929, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.36291184298568435, "learning_rate": 3.330960304618295e-05, "loss": 0.3976, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4190090337105547, "learning_rate": 3.326733686481153e-05, "loss": 0.4012, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.37392989629432727, "learning_rate": 3.3224964598168084e-05, "loss": 0.4065, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.39687199222163744, "learning_rate": 3.318248658506012e-05, "loss": 0.4081, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.35514480277223776, "learning_rate": 3.313990316514069e-05, "loss": 0.3985, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.43534371419641343, "learning_rate": 3.309721467890571e-05, "loss": 0.4008, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.3319803071842582, "learning_rate": 3.305442146769115e-05, "loss": 0.3886, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.36778576585981543, "learning_rate": 3.30115238736704e-05, "loss": 0.3818, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.43062483308158606, "learning_rate": 3.296852223985148e-05, "loss": 0.3975, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4214811921938095, "learning_rate": 3.2925416910074315e-05, "loss": 0.4275, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.3763610876890085, "learning_rate": 3.288220822900796e-05, "loss": 0.4117, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.3454648714711365, "learning_rate": 3.283889654214788e-05, "loss": 0.3872, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.3811713767673218, "learning_rate": 3.279548219581317e-05, "loss": 0.3981, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.3747836861768857, "learning_rate": 3.275196553714379e-05, "loss": 0.4054, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.3740337673252446, "learning_rate": 3.270834691409778e-05, "loss": 0.4266, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.37036457813586926, "learning_rate": 3.266462667544849e-05, "loss": 0.4028, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.33948559939482337, "learning_rate": 3.262080517078178e-05, "loss": 0.392, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.3839594373499604, "learning_rate": 3.257688275049323e-05, "loss": 0.4045, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.33971197030733286, "learning_rate": 3.253285976578535e-05, "loss": 0.4167, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.3637505973106821, "learning_rate": 3.2488736568664756e-05, "loss": 0.401, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.36411358070467764, "learning_rate": 3.244451351193935e-05, "loss": 0.4035, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.349761823980882, "learning_rate": 3.240019094921551e-05, "loss": 0.3887, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.3746468783799437, "learning_rate": 3.235576923489527e-05, "loss": 0.3942, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.40155064113213823, "learning_rate": 3.2311248724173476e-05, "loss": 0.3984, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.3529664634435689, "learning_rate": 3.226662977303494e-05, "loss": 0.3965, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.44952679153045605, "learning_rate": 3.2221912738251626e-05, "loss": 0.3915, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.40125443133857686, "learning_rate": 3.2177097977379736e-05, "loss": 0.3962, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.4104940092408475, "learning_rate": 3.21321858487569e-05, "loss": 0.3752, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.42424903167220906, "learning_rate": 3.208717671149931e-05, "loss": 0.376, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.39345739569437965, "learning_rate": 3.204207092549882e-05, "loss": 0.4014, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.44745237244794633, "learning_rate": 3.19968688514201e-05, "loss": 0.4154, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.37298359634589723, "learning_rate": 3.195157085069774e-05, "loss": 0.4107, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.39544504090701027, "learning_rate": 3.190617728553332e-05, "loss": 0.4014, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.4211491223573765, "learning_rate": 3.1860688518892606e-05, "loss": 0.4046, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.35636146195447876, "learning_rate": 3.181510491450254e-05, "loss": 0.4207, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.4070728843799675, "learning_rate": 3.176942683684842e-05, "loss": 0.3998, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.3368418194020955, "learning_rate": 3.1723654651170934e-05, "loss": 0.4128, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.40179638022094377, "learning_rate": 3.167778872346327e-05, "loss": 0.3889, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.3846601898490665, "learning_rate": 3.163182942046815e-05, "loss": 0.3953, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.38681404103518574, "learning_rate": 3.158577710967494e-05, "loss": 0.4127, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.4123478297647928, "learning_rate": 3.153963215931669e-05, "loss": 0.3918, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.4502956963927718, "learning_rate": 3.14933949383672e-05, "loss": 0.406, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.37971373661542185, "learning_rate": 3.144706581653805e-05, "loss": 0.4089, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.418317315914009, "learning_rate": 3.140064516427566e-05, "loss": 0.391, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.34280100882548115, "learning_rate": 3.135413335275833e-05, "loss": 0.3724, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.43519192392836287, "learning_rate": 3.130753075389327e-05, "loss": 0.41, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.3786075419691357, "learning_rate": 3.1260837740313625e-05, "loss": 0.4318, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.3449941580265357, "learning_rate": 3.121405468537547e-05, "loss": 0.3668, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.36078434982198593, "learning_rate": 3.116718196315488e-05, "loss": 0.3844, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4013548085133474, "learning_rate": 3.1120219948444894e-05, "loss": 0.3971, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.37326463947027094, "learning_rate": 3.107316901675252e-05, "loss": 0.4014, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3354208986481743, "learning_rate": 3.1026029544295745e-05, "loss": 0.3928, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.36748325648406405, "learning_rate": 3.097880190800057e-05, "loss": 0.3983, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.37440519852929377, "learning_rate": 3.093148648549788e-05, "loss": 0.4032, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.38111529619195317, "learning_rate": 3.088408365512055e-05, "loss": 0.4117, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.3821898935008034, "learning_rate": 3.083659379590034e-05, "loss": 0.4098, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.3544242868263318, "learning_rate": 3.0789017287564913e-05, "loss": 0.3877, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.38357919018586506, "learning_rate": 3.074135451053475e-05, "loss": 0.4144, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.40801849065118434, "learning_rate": 3.069360584592015e-05, "loss": 0.395, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.343553241590094, "learning_rate": 3.064577167551816e-05, "loss": 0.399, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.388699898803801, "learning_rate": 3.059785238180953e-05, "loss": 0.3827, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.37640602902760706, "learning_rate": 3.054984834795566e-05, "loss": 0.3733, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.4206564275031684, "learning_rate": 3.0501759957795537e-05, "loss": 0.3854, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.39985277456511653, "learning_rate": 3.0453587595842627e-05, "loss": 0.3903, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4270151710518215, "learning_rate": 3.0405331647281856e-05, "loss": 0.4195, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.45046794784627964, "learning_rate": 3.0356992497966508e-05, "loss": 0.3886, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.430363580634771, "learning_rate": 3.0308570534415137e-05, "loss": 0.4156, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.3878038148146746, "learning_rate": 3.0260066143808467e-05, "loss": 0.3972, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.4551950174056098, "learning_rate": 3.021147971398632e-05, "loss": 0.3971, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.411109966841464, "learning_rate": 3.0162811633444478e-05, "loss": 0.3772, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.38888101834682265, "learning_rate": 3.0114062291331635e-05, "loss": 0.4187, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.41610025405296497, "learning_rate": 3.0065232077446217e-05, "loss": 0.3971, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.43083743384622686, "learning_rate": 3.001632138223332e-05, "loss": 0.3884, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.5434545070898636, "learning_rate": 2.9967330596781565e-05, "loss": 0.3212, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.4464679649582436, "learning_rate": 2.9918260112819952e-05, "loss": 0.2935, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.6471443500796538, "learning_rate": 2.9869110322714778e-05, "loss": 0.3009, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5192756710801764, "learning_rate": 2.9819881619466447e-05, "loss": 0.3041, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.48360722737278744, "learning_rate": 2.9770574396706364e-05, "loss": 0.3466, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.3878484867062741, "learning_rate": 2.972118904869376e-05, "loss": 0.3053, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4072264721266421, "learning_rate": 2.9671725970312563e-05, "loss": 0.3141, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.4688642633029877, "learning_rate": 2.9622185557068238e-05, "loss": 0.3125, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.3887150124767293, "learning_rate": 2.95725682050846e-05, "loss": 0.2889, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.4760117024504767, "learning_rate": 2.9522874311100684e-05, "loss": 0.2939, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.3742135476639349, "learning_rate": 2.9473104272467526e-05, "loss": 0.3076, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4902015157511538, "learning_rate": 2.942325848714505e-05, "loss": 0.3468, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.3775438772819724, "learning_rate": 2.9373337353698804e-05, "loss": 0.2813, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4525788562264909, "learning_rate": 2.932334127129686e-05, "loss": 0.3068, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.36451445193681825, "learning_rate": 2.9273270639706547e-05, "loss": 0.2915, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.39863529683946075, "learning_rate": 2.922312585929131e-05, "loss": 0.3029, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.3840017307722695, "learning_rate": 2.9172907331007478e-05, "loss": 0.3005, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.3472386766222826, "learning_rate": 2.9122615456401053e-05, "loss": 0.3191, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.3555850946317239, "learning_rate": 2.9072250637604535e-05, "loss": 0.293, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3909527774698781, "learning_rate": 2.9021813277333667e-05, "loss": 0.304, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.3447528152416515, "learning_rate": 2.8971303778884244e-05, "loss": 0.2881, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3870382940569285, "learning_rate": 2.8920722546128863e-05, "loss": 0.3051, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.3414557709780728, "learning_rate": 2.887006998351372e-05, "loss": 0.3008, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3708416308579349, "learning_rate": 2.881934649605535e-05, "loss": 0.3, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.36365974713372357, "learning_rate": 2.8768552489337408e-05, "loss": 0.313, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.38903972541010023, "learning_rate": 2.8717688369507425e-05, "loss": 0.3044, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.34834287723926405, "learning_rate": 2.8666754543273535e-05, "loss": 0.3252, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.35209607307646335, "learning_rate": 2.8615751417901273e-05, "loss": 0.287, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3502919596271989, "learning_rate": 2.856467940121025e-05, "loss": 0.2894, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.34461790218509436, "learning_rate": 2.8513538901570964e-05, "loss": 0.2891, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3412572979243248, "learning_rate": 2.846233032790149e-05, "loss": 0.2985, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.37104431605762167, "learning_rate": 2.84110540896642e-05, "loss": 0.2993, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.31929075530182444, "learning_rate": 2.8359710596862555e-05, "loss": 0.2793, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.38953947136476874, "learning_rate": 2.8308300260037734e-05, "loss": 0.3085, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3770275841397494, "learning_rate": 2.8256823490265424e-05, "loss": 0.2993, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3485950389561983, "learning_rate": 2.8205280699152515e-05, "loss": 0.2928, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.3743926092018251, "learning_rate": 2.8153672298833777e-05, "loss": 0.2949, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.38008126757082855, "learning_rate": 2.8101998701968615e-05, "loss": 0.3254, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.35853300715812725, "learning_rate": 2.805026032173773e-05, "loss": 0.2994, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.38815485358054125, "learning_rate": 2.7998457571839832e-05, "loss": 0.2993, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.39091432432206397, "learning_rate": 2.7946590866488322e-05, "loss": 0.2939, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.38454305853902226, "learning_rate": 2.7894660620408e-05, "loss": 0.2885, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.33753326288888735, "learning_rate": 2.784266724883173e-05, "loss": 0.2679, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.40247897489895423, "learning_rate": 2.7790611167497128e-05, "loss": 0.311, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.33760651727450003, "learning_rate": 2.7738492792643224e-05, "loss": 0.3089, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.37860451289403446, "learning_rate": 2.768631254100716e-05, "loss": 0.2983, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3055128058137442, "learning_rate": 2.7634070829820836e-05, "loss": 0.3121, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.4011489697819905, "learning_rate": 2.7581768076807592e-05, "loss": 0.292, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.32775022098075474, "learning_rate": 2.7529404700178832e-05, "loss": 0.294, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3919246231777275, "learning_rate": 2.7476981118630735e-05, "loss": 0.2985, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.37744832538317946, "learning_rate": 2.742449775134085e-05, "loss": 0.3044, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.3545992779889331, "learning_rate": 2.7371955017964788e-05, "loss": 0.2813, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.3691964457666949, "learning_rate": 2.7319353338632845e-05, "loss": 0.2963, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.35132806309544956, "learning_rate": 2.7266693133946645e-05, "loss": 0.2897, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.38308182466996504, "learning_rate": 2.7213974824975785e-05, "loss": 0.3102, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.36001347752829715, "learning_rate": 2.7161198833254464e-05, "loss": 0.2912, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.40633226301690517, "learning_rate": 2.7108365580778095e-05, "loss": 0.2932, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3808509727705208, "learning_rate": 2.705547548999996e-05, "loss": 0.2931, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.38016141248268975, "learning_rate": 2.7002528983827817e-05, "loss": 0.2983, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3813506078883797, "learning_rate": 2.6949526485620517e-05, "loss": 0.329, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.372199528335091, "learning_rate": 2.6896468419184623e-05, "loss": 0.314, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.39751054708011574, "learning_rate": 2.6843355208771024e-05, "loss": 0.2986, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.35649937951776295, "learning_rate": 2.6790187279071536e-05, "loss": 0.2998, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.3687505414160794, "learning_rate": 2.67369650552155e-05, "loss": 0.3045, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.3665759350191675, "learning_rate": 2.6683688962766407e-05, "loss": 0.2905, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.371041741732559, "learning_rate": 2.6630359427718468e-05, "loss": 0.3042, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3400647113906577, "learning_rate": 2.6576976876493225e-05, "loss": 0.3005, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3717011666310005, "learning_rate": 2.652354173593614e-05, "loss": 0.2917, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.372335701589871, "learning_rate": 2.647005443331317e-05, "loss": 0.3245, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3826278538014346, "learning_rate": 2.6416515396307354e-05, "loss": 0.3022, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3632452273323238, "learning_rate": 2.636292505301542e-05, "loss": 0.2904, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3880501352588757, "learning_rate": 2.630928383194431e-05, "loss": 0.2835, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.34424346591401156, "learning_rate": 2.625559216200781e-05, "loss": 0.31, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3908420879716786, "learning_rate": 2.620185047252308e-05, "loss": 0.3172, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.3498470380031152, "learning_rate": 2.614805919320723e-05, "loss": 0.3098, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3756817593392162, "learning_rate": 2.6094218754173895e-05, "loss": 0.2999, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3419443143834042, "learning_rate": 2.60403295859298e-05, "loss": 0.3064, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3761018143371604, "learning_rate": 2.5986392119371297e-05, "loss": 0.3126, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.34326577138723585, "learning_rate": 2.5932406785780928e-05, "loss": 0.3065, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3807476808189649, "learning_rate": 2.5878374016823987e-05, "loss": 0.312, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.32098736299028974, "learning_rate": 2.5824294244545045e-05, "loss": 0.3144, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.4281977201184803, "learning_rate": 2.577016790136453e-05, "loss": 0.2965, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3408109982974224, "learning_rate": 2.5715995420075225e-05, "loss": 0.2959, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.376206489035664, "learning_rate": 2.5661777233838864e-05, "loss": 0.2896, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.43353586725347465, "learning_rate": 2.5607513776182616e-05, "loss": 0.303, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.31115266588467777, "learning_rate": 2.5553205480995633e-05, "loss": 0.3029, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.42850997956536885, "learning_rate": 2.5498852782525604e-05, "loss": 0.3062, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3599927330007983, "learning_rate": 2.5444456115375252e-05, "loss": 0.2874, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.38748687104265733, "learning_rate": 2.539001591449889e-05, "loss": 0.3088, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.3763459553932042, "learning_rate": 2.53355326151989e-05, "loss": 0.2865, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.36865305779042, "learning_rate": 2.5281006653122288e-05, "loss": 0.3238, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.38389026914458896, "learning_rate": 2.5226438464257217e-05, "loss": 0.3081, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.36842412829767274, "learning_rate": 2.5171828484929447e-05, "loss": 0.3315, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3552261599245639, "learning_rate": 2.5117177151798934e-05, "loss": 0.3149, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.39629003083145103, "learning_rate": 2.506248490185627e-05, "loss": 0.3196, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.32643817141681786, "learning_rate": 2.500775217241923e-05, "loss": 0.2964, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4303264777448928, "learning_rate": 2.4952979401129266e-05, "loss": 0.2919, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3455579549483282, "learning_rate": 2.4898167025948e-05, "loss": 0.3013, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.36832557322019466, "learning_rate": 2.4843315485153703e-05, "loss": 0.3105, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.38156542635401275, "learning_rate": 2.4788425217337856e-05, "loss": 0.2812, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.35481810807442116, "learning_rate": 2.4733496661401572e-05, "loss": 0.2962, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.37181126430381395, "learning_rate": 2.4678530256552114e-05, "loss": 0.306, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.4334174560645448, "learning_rate": 2.46235264422994e-05, "loss": 0.3097, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.5301000424906273, "learning_rate": 2.4568485658452452e-05, "loss": 0.3286, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.3936215130203227, "learning_rate": 2.451340834511592e-05, "loss": 0.2906, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.3279054349550985, "learning_rate": 2.4458294942686528e-05, "loss": 0.3048, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.33208065353876653, "learning_rate": 2.440314589184958e-05, "loss": 0.2925, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.35774885933271533, "learning_rate": 2.434796163357541e-05, "loss": 0.3048, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.32697137179217817, "learning_rate": 2.429274260911588e-05, "loss": 0.2977, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.30538324171700515, "learning_rate": 2.423748926000084e-05, "loss": 0.2958, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.33052287989037527, "learning_rate": 2.418220202803459e-05, "loss": 0.3058, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.35703021682337654, "learning_rate": 2.412688135529237e-05, "loss": 0.3051, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3327627975156861, "learning_rate": 2.4071527684116807e-05, "loss": 0.2922, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.3387567204381427, "learning_rate": 2.4016141457114372e-05, "loss": 0.3268, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.3331643328001185, "learning_rate": 2.396072311715187e-05, "loss": 0.2944, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3436723922637314, "learning_rate": 2.3905273107352863e-05, "loss": 0.2979, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.308754334387179, "learning_rate": 2.3849791871094157e-05, "loss": 0.326, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.35029772545337595, "learning_rate": 2.379427985200223e-05, "loss": 0.2992, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.32159794851954726, "learning_rate": 2.373873749394972e-05, "loss": 0.3228, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.2895015075568991, "learning_rate": 2.3683165241051836e-05, "loss": 0.3098, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.32905897492255476, "learning_rate": 2.3627563537662823e-05, "loss": 0.3143, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.3074356954651175, "learning_rate": 2.3571932828372433e-05, "loss": 0.3046, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3186180206197389, "learning_rate": 2.351627355800233e-05, "loss": 0.3079, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.30536903410640964, "learning_rate": 2.346058617160256e-05, "loss": 0.2906, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.32698154412034963, "learning_rate": 2.3404871114447976e-05, "loss": 0.2988, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3220520090747277, "learning_rate": 2.334912883203469e-05, "loss": 0.2776, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3571972095025525, "learning_rate": 2.3293359770076505e-05, "loss": 0.3098, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.3190825627430738, "learning_rate": 2.323756437450136e-05, "loss": 0.3064, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.33500585566738117, "learning_rate": 2.3181743091447754e-05, "loss": 0.2824, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.33668437149079955, "learning_rate": 2.3125896367261164e-05, "loss": 0.2955, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.34421752219868423, "learning_rate": 2.307002464849052e-05, "loss": 0.2792, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.3807315904946477, "learning_rate": 2.30141283818846e-05, "loss": 0.294, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.34785838025260274, "learning_rate": 2.2958208014388462e-05, "loss": 0.3123, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3528567751256178, "learning_rate": 2.2902263993139857e-05, "loss": 0.2909, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.31454129203879005, "learning_rate": 2.2846296765465708e-05, "loss": 0.29, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.34392719359546786, "learning_rate": 2.2790306778878465e-05, "loss": 0.3156, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.309449153198366, "learning_rate": 2.273429448107257e-05, "loss": 0.3178, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.338411250628157, "learning_rate": 2.2678260319920868e-05, "loss": 0.2863, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.30276181065853325, "learning_rate": 2.262220474347102e-05, "loss": 0.3195, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3201728723182471, "learning_rate": 2.2566128199941918e-05, "loss": 0.309, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.31102816107055403, "learning_rate": 2.2510031137720104e-05, "loss": 0.3062, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.3064721436216739, "learning_rate": 2.2453914005356206e-05, "loss": 0.2918, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.3104601622829959, "learning_rate": 2.2397777251561302e-05, "loss": 0.2983, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3543721367092432, "learning_rate": 2.2341621325203393e-05, "loss": 0.285, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3360704202984971, "learning_rate": 2.2285446675303764e-05, "loss": 0.3092, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.3264300384148773, "learning_rate": 2.2229253751033423e-05, "loss": 0.2863, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.30484811614440654, "learning_rate": 2.2173043001709492e-05, "loss": 0.3157, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3350004330884979, "learning_rate": 2.2116814876791627e-05, "loss": 0.3273, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.35214710928464005, "learning_rate": 2.2060569825878413e-05, "loss": 0.2776, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.3294696373717883, "learning_rate": 2.2004308298703777e-05, "loss": 0.2936, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.35191064515518855, "learning_rate": 2.1948030745133396e-05, "loss": 0.3119, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.33793559653281624, "learning_rate": 2.1891737615161083e-05, "loss": 0.2742, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3264800976238027, "learning_rate": 2.1835429358905218e-05, "loss": 0.2977, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3178223630500418, "learning_rate": 2.17791064266051e-05, "loss": 0.3318, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.3369912381331842, "learning_rate": 2.172276926861741e-05, "loss": 0.3003, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.3372131455165883, "learning_rate": 2.166641833541255e-05, "loss": 0.3192, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3662891385474818, "learning_rate": 2.161005407757109e-05, "loss": 0.3024, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3390417905859456, "learning_rate": 2.155367694578013e-05, "loss": 0.3104, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.34566832214466137, "learning_rate": 2.1497287390829712e-05, "loss": 0.2908, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.3302115431631988, "learning_rate": 2.1440885863609208e-05, "loss": 0.3077, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.2878361838344184, "learning_rate": 2.1384472815103737e-05, "loss": 0.2971, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3199876842734431, "learning_rate": 2.1328048696390534e-05, "loss": 0.3015, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.33683041134150304, "learning_rate": 2.1271613958635342e-05, "loss": 0.3126, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.3333277422809193, "learning_rate": 2.1215169053088825e-05, "loss": 0.3066, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.30559600573164725, "learning_rate": 2.1158714431082937e-05, "loss": 0.3194, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.33466294463125923, "learning_rate": 2.110225054402733e-05, "loss": 0.2852, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.342435060538408, "learning_rate": 2.1045777843405747e-05, "loss": 0.307, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.32415881589724066, "learning_rate": 2.09892967807724e-05, "loss": 0.3003, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3429714595156985, "learning_rate": 2.093280780774835e-05, "loss": 0.329, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.30931636996845074, "learning_rate": 2.087631137601793e-05, "loss": 0.3148, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3507872074226158, "learning_rate": 2.0819807937325104e-05, "loss": 0.308, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.30341590930753354, "learning_rate": 2.0763297943469847e-05, "loss": 0.2963, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.3280430351293843, "learning_rate": 2.070678184630458e-05, "loss": 0.3199, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.3036792171826175, "learning_rate": 2.06502600977305e-05, "loss": 0.3162, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3040616976319838, "learning_rate": 2.0593733149694008e-05, "loss": 0.2956, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3283221493871188, "learning_rate": 2.0537201454183074e-05, "loss": 0.3038, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3078160993191753, "learning_rate": 2.0480665463223626e-05, "loss": 0.3164, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3166898770120176, "learning_rate": 2.042412562887594e-05, "loss": 0.3176, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3050720760522145, "learning_rate": 2.0367582403231033e-05, "loss": 0.3008, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.32516350831390217, "learning_rate": 2.0311036238407023e-05, "loss": 0.2879, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.3034147626148467, "learning_rate": 2.0254487586545534e-05, "loss": 0.2978, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3488865520833733, "learning_rate": 2.0197936899808088e-05, "loss": 0.315, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3554382282328362, "learning_rate": 2.0141384630372466e-05, "loss": 0.3134, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.32652312936489797, "learning_rate": 2.0084831230429106e-05, "loss": 0.2958, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.3642505672073948, "learning_rate": 2.0028277152177492e-05, "loss": 0.3094, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.35843037005308104, "learning_rate": 1.9971722847822518e-05, "loss": 0.2982, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.30950273876360485, "learning_rate": 1.99151687695709e-05, "loss": 0.3038, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.3783286441842929, "learning_rate": 1.9858615369627537e-05, "loss": 0.2996, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.3372250817294755, "learning_rate": 1.9802063100191916e-05, "loss": 0.3052, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.3206331614426604, "learning_rate": 1.974551241345447e-05, "loss": 0.2943, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.32891515530338283, "learning_rate": 1.9688963761592984e-05, "loss": 0.3188, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.2991105789382652, "learning_rate": 1.963241759676897e-05, "loss": 0.3137, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.31108717588695806, "learning_rate": 1.9575874371124066e-05, "loss": 0.2875, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.3222826171864066, "learning_rate": 1.951933453677638e-05, "loss": 0.3117, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.31114905910642904, "learning_rate": 1.9462798545816932e-05, "loss": 0.3117, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.2965007923335108, "learning_rate": 1.9406266850305996e-05, "loss": 0.2772, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.30964365704199653, "learning_rate": 1.9349739902269503e-05, "loss": 0.3011, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3060938913976646, "learning_rate": 1.9293218153695425e-05, "loss": 0.2783, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.31592760674173764, "learning_rate": 1.9236702056530153e-05, "loss": 0.2972, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.32015690029256344, "learning_rate": 1.9180192062674907e-05, "loss": 0.3012, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.3961896281845294, "learning_rate": 1.9123688623982076e-05, "loss": 0.3134, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.32172782371414843, "learning_rate": 1.906719219225165e-05, "loss": 0.2974, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.31407397428693457, "learning_rate": 1.9010703219227603e-05, "loss": 0.3093, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.30698241477679217, "learning_rate": 1.8954222156594256e-05, "loss": 0.3203, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.29603366070452036, "learning_rate": 1.8897749455972673e-05, "loss": 0.3144, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.371002996275762, "learning_rate": 1.884128556891707e-05, "loss": 0.2834, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.29674817744282095, "learning_rate": 1.878483094691119e-05, "loss": 0.3172, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.30830605593906796, "learning_rate": 1.8728386041364664e-05, "loss": 0.2948, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.4386212521995221, "learning_rate": 1.867195130360947e-05, "loss": 0.2991, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3086245024431807, "learning_rate": 1.8615527184896263e-05, "loss": 0.3029, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.31644282985710165, "learning_rate": 1.8559114136390795e-05, "loss": 0.2932, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.2993790970409678, "learning_rate": 1.8502712609170298e-05, "loss": 0.2911, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.5130320294182513, "learning_rate": 1.8446323054219876e-05, "loss": 0.2973, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.29378855644311147, "learning_rate": 1.838994592242891e-05, "loss": 0.2997, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.33232956902970606, "learning_rate": 1.8333581664587453e-05, "loss": 0.3125, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3313754670987868, "learning_rate": 1.8277230731382593e-05, "loss": 0.3083, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3143977560544285, "learning_rate": 1.82208935733949e-05, "loss": 0.2928, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.354666873275203, "learning_rate": 1.8164570641094793e-05, "loss": 0.3133, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3482649365465392, "learning_rate": 1.810826238483892e-05, "loss": 0.3037, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.3354680161035837, "learning_rate": 1.8051969254866608e-05, "loss": 0.3023, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.30079123997570656, "learning_rate": 1.7995691701296226e-05, "loss": 0.2945, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.3183302956129432, "learning_rate": 1.7939430174121593e-05, "loss": 0.3097, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.3045624407059261, "learning_rate": 1.788318512320838e-05, "loss": 0.2831, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3132700087798239, "learning_rate": 1.782695699829051e-05, "loss": 0.289, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.3081469529944052, "learning_rate": 1.7770746248966587e-05, "loss": 0.2935, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.2980028921633926, "learning_rate": 1.7714553324696243e-05, "loss": 0.3049, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.32265009229569663, "learning_rate": 1.7658378674796614e-05, "loss": 0.3004, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3055701746379578, "learning_rate": 1.76022227484387e-05, "loss": 0.3022, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.3100411468151258, "learning_rate": 1.7546085994643807e-05, "loss": 0.308, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.3052953966203851, "learning_rate": 1.7489968862279902e-05, "loss": 0.3002, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3124105982559717, "learning_rate": 1.743387180005809e-05, "loss": 0.3118, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.30552466211344315, "learning_rate": 1.737779525652899e-05, "loss": 0.3065, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.31457999346819654, "learning_rate": 1.732173968007914e-05, "loss": 0.2877, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.29662753599359787, "learning_rate": 1.7265705518927437e-05, "loss": 0.283, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.29582260649529735, "learning_rate": 1.7209693221121542e-05, "loss": 0.296, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.3341057808723812, "learning_rate": 1.7153703234534302e-05, "loss": 0.3043, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.28794144492277685, "learning_rate": 1.709773600686015e-05, "loss": 0.3189, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.3431448399555632, "learning_rate": 1.7041791985611548e-05, "loss": 0.312, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.3310528484147487, "learning_rate": 1.69858716181154e-05, "loss": 0.2727, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.34013438076967684, "learning_rate": 1.692997535150948e-05, "loss": 0.3165, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.2884640333921777, "learning_rate": 1.687410363273884e-05, "loss": 0.3018, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3260191545132105, "learning_rate": 1.6818256908552257e-05, "loss": 0.298, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3063298599854527, "learning_rate": 1.6762435625498646e-05, "loss": 0.2963, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3049136912700093, "learning_rate": 1.67066402299235e-05, "loss": 0.2855, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.34349065435669285, "learning_rate": 1.6650871167965313e-05, "loss": 0.3022, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.3169029781161856, "learning_rate": 1.6595128885552028e-05, "loss": 0.3045, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.30772849974308025, "learning_rate": 1.653941382839745e-05, "loss": 0.3148, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.5399735014936312, "learning_rate": 1.6483726441997673e-05, "loss": 0.2105, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.31368546731056324, "learning_rate": 1.642806717162757e-05, "loss": 0.224, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.7027071903066137, "learning_rate": 1.637243646233718e-05, "loss": 0.2409, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.3859569070755882, "learning_rate": 1.6316834758948174e-05, "loss": 0.2245, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.47260107061193063, "learning_rate": 1.6261262506050282e-05, "loss": 0.2143, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4610175919593757, "learning_rate": 1.620572014799777e-05, "loss": 0.2221, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.3723639934740733, "learning_rate": 1.6150208128905857e-05, "loss": 0.2191, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.404145181956363, "learning_rate": 1.6094726892647147e-05, "loss": 0.2389, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.4051304699602178, "learning_rate": 1.6039276882848135e-05, "loss": 0.2358, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.36687941662300244, "learning_rate": 1.5983858542885635e-05, "loss": 0.2572, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.34662260243373844, "learning_rate": 1.5928472315883203e-05, "loss": 0.232, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.33933120708559517, "learning_rate": 1.5873118644707633e-05, "loss": 0.2055, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.35871596212012696, "learning_rate": 1.5817797971965413e-05, "loss": 0.2169, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.31389454152899426, "learning_rate": 1.576251073999917e-05, "loss": 0.2188, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.3350773415186487, "learning_rate": 1.5707257390884126e-05, "loss": 0.2306, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.3210160374884676, "learning_rate": 1.5652038366424595e-05, "loss": 0.2229, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.326811221075854, "learning_rate": 1.5596854108150424e-05, "loss": 0.2135, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.35944406729084444, "learning_rate": 1.5541705057313476e-05, "loss": 0.2134, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3054157140338714, "learning_rate": 1.5486591654884086e-05, "loss": 0.2372, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3780863897278674, "learning_rate": 1.543151434154755e-05, "loss": 0.2311, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.3108798156833026, "learning_rate": 1.5376473557700615e-05, "loss": 0.2227, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.30981824960516463, "learning_rate": 1.5321469743447893e-05, "loss": 0.2232, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.3308138678094447, "learning_rate": 1.5266503338598434e-05, "loss": 0.2107, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.310924273639795, "learning_rate": 1.5211574782662149e-05, "loss": 0.2418, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.29542065193108447, "learning_rate": 1.5156684514846307e-05, "loss": 0.2114, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3174963425028653, "learning_rate": 1.5101832974052012e-05, "loss": 0.2469, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.29901394224182926, "learning_rate": 1.5047020598870737e-05, "loss": 0.2245, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2841861195816376, "learning_rate": 1.4992247827580778e-05, "loss": 0.2288, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.301587580163349, "learning_rate": 1.493751509814374e-05, "loss": 0.2179, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.303355272756949, "learning_rate": 1.4882822848201073e-05, "loss": 0.22, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.28129003654132156, "learning_rate": 1.4828171515070553e-05, "loss": 0.2087, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2804406837266875, "learning_rate": 1.4773561535742793e-05, "loss": 0.2175, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.2923100753236069, "learning_rate": 1.4718993346877715e-05, "loss": 0.2188, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.2805159501930072, "learning_rate": 1.466446738480111e-05, "loss": 0.2262, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.27628714850222535, "learning_rate": 1.460998408550112e-05, "loss": 0.2139, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3226069529326036, "learning_rate": 1.4555543884624751e-05, "loss": 0.239, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.291525310860608, "learning_rate": 1.4501147217474402e-05, "loss": 0.2094, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.26016297849000836, "learning_rate": 1.444679451900437e-05, "loss": 0.2153, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.30106134709370336, "learning_rate": 1.4392486223817397e-05, "loss": 0.2346, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2935532894754158, "learning_rate": 1.4338222766161143e-05, "loss": 0.2235, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2782599771185324, "learning_rate": 1.4284004579924777e-05, "loss": 0.233, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.2738921574482772, "learning_rate": 1.4229832098635479e-05, "loss": 0.2468, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.29325417716834684, "learning_rate": 1.4175705755454963e-05, "loss": 0.1959, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2919123207774825, "learning_rate": 1.412162598317602e-05, "loss": 0.2252, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.2746916458920482, "learning_rate": 1.406759321421907e-05, "loss": 0.2201, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2825835320526499, "learning_rate": 1.401360788062871e-05, "loss": 0.2241, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.285668209900613, "learning_rate": 1.3959670414070204e-05, "loss": 0.2491, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.29640099304080275, "learning_rate": 1.3905781245826108e-05, "loss": 0.2206, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.26555443692912617, "learning_rate": 1.3851940806792778e-05, "loss": 0.2141, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.2836270259332471, "learning_rate": 1.379814952747693e-05, "loss": 0.2179, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.3033394933607459, "learning_rate": 1.3744407837992193e-05, "loss": 0.2102, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2766659585675992, "learning_rate": 1.3690716168055692e-05, "loss": 0.2224, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.3052607942571698, "learning_rate": 1.363707494698459e-05, "loss": 0.2074, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.30734055627339635, "learning_rate": 1.358348460369265e-05, "loss": 0.2111, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2789702064864668, "learning_rate": 1.352994556668684e-05, "loss": 0.2136, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.2954958873782753, "learning_rate": 1.3476458264063865e-05, "loss": 0.2209, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.285066156992124, "learning_rate": 1.342302312350678e-05, "loss": 0.2306, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.27010408345651904, "learning_rate": 1.3369640572281537e-05, "loss": 0.2177, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.3017258138980361, "learning_rate": 1.3316311037233596e-05, "loss": 0.2042, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.289862255689608, "learning_rate": 1.326303494478451e-05, "loss": 0.227, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.2860137684556308, "learning_rate": 1.3209812720928472e-05, "loss": 0.2519, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.29280911761184153, "learning_rate": 1.315664479122898e-05, "loss": 0.2254, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.2903072129986107, "learning_rate": 1.3103531580815378e-05, "loss": 0.237, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.29035607226030424, "learning_rate": 1.3050473514379488e-05, "loss": 0.2202, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2804425411773666, "learning_rate": 1.2997471016172188e-05, "loss": 0.223, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.26881245651676816, "learning_rate": 1.2944524510000042e-05, "loss": 0.21, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2934595235825087, "learning_rate": 1.2891634419221908e-05, "loss": 0.2475, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.2659215240705643, "learning_rate": 1.2838801166745545e-05, "loss": 0.2047, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.2718109744426757, "learning_rate": 1.2786025175024216e-05, "loss": 0.2358, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.2541654490604403, "learning_rate": 1.2733306866053357e-05, "loss": 0.1995, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2673330757227002, "learning_rate": 1.2680646661367163e-05, "loss": 0.2199, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.26029387948419097, "learning_rate": 1.2628044982035219e-05, "loss": 0.2291, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.2665166900048754, "learning_rate": 1.2575502248659155e-05, "loss": 0.2291, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.26833069728814213, "learning_rate": 1.2523018881369269e-05, "loss": 0.2168, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2690754504029025, "learning_rate": 1.2470595299821176e-05, "loss": 0.2285, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2734055377457343, "learning_rate": 1.2418231923192416e-05, "loss": 0.2341, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.27056010423750787, "learning_rate": 1.2365929170179165e-05, "loss": 0.2355, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.26551188303889833, "learning_rate": 1.2313687458992848e-05, "loss": 0.2484, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.2777035695593665, "learning_rate": 1.2261507207356785e-05, "loss": 0.2121, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.2599451760246495, "learning_rate": 1.220938883250288e-05, "loss": 0.2448, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.26573762264502243, "learning_rate": 1.215733275116827e-05, "loss": 0.2268, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.26049317447822884, "learning_rate": 1.2105339379592005e-05, "loss": 0.2223, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.2664488103843918, "learning_rate": 1.2053409133511681e-05, "loss": 0.212, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.2689050908251223, "learning_rate": 1.2001542428160173e-05, "loss": 0.2503, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2557510598876227, "learning_rate": 1.1949739678262278e-05, "loss": 0.2363, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.28445121671084506, "learning_rate": 1.189800129803139e-05, "loss": 0.2116, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.2522245504199912, "learning_rate": 1.1846327701166228e-05, "loss": 0.2149, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.27754549151876384, "learning_rate": 1.1794719300847493e-05, "loss": 0.2128, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2738121230305151, "learning_rate": 1.1743176509734582e-05, "loss": 0.2386, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.27191009261712223, "learning_rate": 1.1691699739962275e-05, "loss": 0.2448, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.2647278680522905, "learning_rate": 1.1640289403137456e-05, "loss": 0.2065, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.25898473545536654, "learning_rate": 1.1588945910335802e-05, "loss": 0.2174, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.2874735764184234, "learning_rate": 1.1537669672098517e-05, "loss": 0.2275, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.26994981891211495, "learning_rate": 1.1486461098429036e-05, "loss": 0.2467, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.26063021685924287, "learning_rate": 1.1435320598789747e-05, "loss": 0.2431, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.24938680922261222, "learning_rate": 1.1384248582098736e-05, "loss": 0.2202, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.2603907644229585, "learning_rate": 1.1333245456726467e-05, "loss": 0.2288, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2553331509281181, "learning_rate": 1.128231163049258e-05, "loss": 0.2335, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2622568825092049, "learning_rate": 1.123144751066259e-05, "loss": 0.1957, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2575120034771352, "learning_rate": 1.1180653503944657e-05, "loss": 0.2149, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.2577591126853098, "learning_rate": 1.1129930016486287e-05, "loss": 0.2095, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.265886990139879, "learning_rate": 1.107927745387114e-05, "loss": 0.2184, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.27883572867670986, "learning_rate": 1.1028696221115766e-05, "loss": 0.2362, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2561670886632442, "learning_rate": 1.0978186722666341e-05, "loss": 0.2268, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.26381349908671875, "learning_rate": 1.0927749362395475e-05, "loss": 0.2409, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.2662446397427181, "learning_rate": 1.0877384543598954e-05, "loss": 0.2365, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2594254413671288, "learning_rate": 1.0827092668992529e-05, "loss": 0.2012, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.28762093128981403, "learning_rate": 1.077687414070869e-05, "loss": 0.1983, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.25947983291843624, "learning_rate": 1.0726729360293451e-05, "loss": 0.2014, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.2659425313631785, "learning_rate": 1.0676658728703147e-05, "loss": 0.2298, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.26756973377181686, "learning_rate": 1.0626662646301198e-05, "loss": 0.2179, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2673111453597031, "learning_rate": 1.0576741512854958e-05, "loss": 0.2322, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.25763224970561316, "learning_rate": 1.052689572753247e-05, "loss": 0.2285, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2717012665034249, "learning_rate": 1.0477125688899328e-05, "loss": 0.2164, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.25393794744040066, "learning_rate": 1.0427431794915406e-05, "loss": 0.22, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.260987306955921, "learning_rate": 1.0377814442931769e-05, "loss": 0.2376, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2736301563275623, "learning_rate": 1.0328274029687439e-05, "loss": 0.2075, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2623852052732069, "learning_rate": 1.0278810951306253e-05, "loss": 0.2378, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.26422913186396346, "learning_rate": 1.0229425603293647e-05, "loss": 0.2319, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.2755249894996114, "learning_rate": 1.0180118380533558e-05, "loss": 0.2091, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2605951582588121, "learning_rate": 1.0130889677285225e-05, "loss": 0.2126, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.273852515764932, "learning_rate": 1.008173988718005e-05, "loss": 0.2274, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2656919375378131, "learning_rate": 1.0032669403218439e-05, "loss": 0.2081, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.2569899857023549, "learning_rate": 9.983678617766677e-06, "loss": 0.2093, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.276805074294481, "learning_rate": 9.934767922553788e-06, "loss": 0.2059, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2576239824115474, "learning_rate": 9.885937708668371e-06, "loss": 0.2228, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.26416474578404503, "learning_rate": 9.837188366555524e-06, "loss": 0.2228, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.27299471102469164, "learning_rate": 9.788520286013691e-06, "loss": 0.2303, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.25655884651284744, "learning_rate": 9.739933856191537e-06, "loss": 0.2024, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2710031835188518, "learning_rate": 9.691429465584866e-06, "loss": 0.2254, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.25510097923066133, "learning_rate": 9.643007502033492e-06, "loss": 0.2115, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.26295435174487114, "learning_rate": 9.594668352718152e-06, "loss": 0.216, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.2571059359630275, "learning_rate": 9.546412404157383e-06, "loss": 0.2065, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.2767358037013547, "learning_rate": 9.498240042204471e-06, "loss": 0.2349, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.24927038666567278, "learning_rate": 9.450151652044339e-06, "loss": 0.2315, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.25747816604647733, "learning_rate": 9.402147618190472e-06, "loss": 0.2267, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.25195839750789445, "learning_rate": 9.354228324481841e-06, "loss": 0.2134, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.2586482832027313, "learning_rate": 9.306394154079852e-06, "loss": 0.2202, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.2551491098501084, "learning_rate": 9.258645489465254e-06, "loss": 0.2129, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.2595881845924708, "learning_rate": 9.21098271243509e-06, "loss": 0.2088, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.27114442503319547, "learning_rate": 9.163406204099659e-06, "loss": 0.2241, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.2594922911304568, "learning_rate": 9.115916344879452e-06, "loss": 0.2124, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.26567989400930336, "learning_rate": 9.068513514502126e-06, "loss": 0.2203, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.26993997840688105, "learning_rate": 9.021198091999439e-06, "loss": 0.2334, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.24879142976732982, "learning_rate": 8.973970455704251e-06, "loss": 0.2281, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.25522304078574504, "learning_rate": 8.926830983247495e-06, "loss": 0.225, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2594502219434665, "learning_rate": 8.879780051555116e-06, "loss": 0.2293, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.25001901258681847, "learning_rate": 8.83281803684512e-06, "loss": 0.2188, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.24950270142431016, "learning_rate": 8.785945314624532e-06, "loss": 0.218, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.2555429133139492, "learning_rate": 8.739162259686385e-06, "loss": 0.2223, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.26322820684896536, "learning_rate": 8.692469246106734e-06, "loss": 0.2128, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.2572274059758806, "learning_rate": 8.645866647241677e-06, "loss": 0.2438, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2634035120408966, "learning_rate": 8.599354835724348e-06, "loss": 0.2332, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2735741230731836, "learning_rate": 8.552934183461958e-06, "loss": 0.2265, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.24299899924728588, "learning_rate": 8.506605061632805e-06, "loss": 0.2485, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.25787613113387353, "learning_rate": 8.460367840683308e-06, "loss": 0.2288, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.26515866884560785, "learning_rate": 8.414222890325065e-06, "loss": 0.2082, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 1.1593813671815372, "learning_rate": 8.368170579531855e-06, "loss": 0.2791, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.2603253456790053, "learning_rate": 8.322211276536733e-06, "loss": 0.2227, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.25874529042249667, "learning_rate": 8.27634534882907e-06, "loss": 0.2343, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.24711368439926756, "learning_rate": 8.230573163151585e-06, "loss": 0.2286, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.24358458477268186, "learning_rate": 8.184895085497466e-06, "loss": 0.2531, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.25331227038678206, "learning_rate": 8.139311481107401e-06, "loss": 0.2166, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.27200080213674394, "learning_rate": 8.093822714466686e-06, "loss": 0.2309, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.25879428804450433, "learning_rate": 8.048429149302271e-06, "loss": 0.2377, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2590048130106444, "learning_rate": 8.003131148579902e-06, "loss": 0.2071, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.26649898565443464, "learning_rate": 7.957929074501182e-06, "loss": 0.2375, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.27851100611923435, "learning_rate": 7.912823288500695e-06, "loss": 0.2274, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.25440007386148017, "learning_rate": 7.867814151243102e-06, "loss": 0.2144, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2618585394914014, "learning_rate": 7.822902022620267e-06, "loss": 0.2011, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.27568613585176405, "learning_rate": 7.778087261748377e-06, "loss": 0.2285, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.2587536458230549, "learning_rate": 7.733370226965056e-06, "loss": 0.1984, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2550360142136901, "learning_rate": 7.688751275826527e-06, "loss": 0.2147, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2547198024338684, "learning_rate": 7.644230765104735e-06, "loss": 0.2184, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.27315274166724657, "learning_rate": 7.599809050784502e-06, "loss": 0.2267, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.24467218167677507, "learning_rate": 7.555486488060661e-06, "loss": 0.21, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2594379883906387, "learning_rate": 7.511263431335249e-06, "loss": 0.2019, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.26108336369035257, "learning_rate": 7.467140234214656e-06, "loss": 0.2346, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.25196456011668217, "learning_rate": 7.423117249506777e-06, "loss": 0.2252, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.2484688876597165, "learning_rate": 7.379194829218231e-06, "loss": 0.2365, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.24921146958803841, "learning_rate": 7.335373324551518e-06, "loss": 0.1991, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.25012028363368155, "learning_rate": 7.291653085902224e-06, "loss": 0.2347, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.25168286650135546, "learning_rate": 7.248034462856213e-06, "loss": 0.2226, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2593386547170394, "learning_rate": 7.20451780418683e-06, "loss": 0.2312, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2523945935082095, "learning_rate": 7.161103457852128e-06, "loss": 0.203, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.25107927180455075, "learning_rate": 7.117791770992046e-06, "loss": 0.2283, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.2557457961203567, "learning_rate": 7.074583089925688e-06, "loss": 0.2339, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.25614264323832175, "learning_rate": 7.0314777601485155e-06, "loss": 0.2304, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.25586689874288654, "learning_rate": 6.988476126329604e-06, "loss": 0.2207, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.254939345898195, "learning_rate": 6.945578532308857e-06, "loss": 0.2092, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.2605156080055185, "learning_rate": 6.902785321094301e-06, "loss": 0.1947, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.27315032899100583, "learning_rate": 6.8600968348593115e-06, "loss": 0.2304, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2636415188962318, "learning_rate": 6.817513414939892e-06, "loss": 0.2146, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.25852948004159193, "learning_rate": 6.775035401831924e-06, "loss": 0.206, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.2459254321032096, "learning_rate": 6.732663135188473e-06, "loss": 0.2206, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.2659225659498665, "learning_rate": 6.690396953817055e-06, "loss": 0.2128, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.248543773886396, "learning_rate": 6.648237195676927e-06, "loss": 0.2264, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.25130509943675666, "learning_rate": 6.606184197876395e-06, "loss": 0.2295, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.2594648844238782, "learning_rate": 6.564238296670109e-06, "loss": 0.2221, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.25692139863583086, "learning_rate": 6.52239982745638e-06, "loss": 0.2222, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.25135208833305484, "learning_rate": 6.480669124774484e-06, "loss": 0.1865, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.2687222012248839, "learning_rate": 6.439046522302013e-06, "loss": 0.2124, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.2534033686986372, "learning_rate": 6.397532352852191e-06, "loss": 0.1988, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.24787485825869923, "learning_rate": 6.356126948371202e-06, "loss": 0.2532, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.24118854193165334, "learning_rate": 6.314830639935559e-06, "loss": 0.2263, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.25121938192080473, "learning_rate": 6.273643757749448e-06, "loss": 0.2214, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.2612891279183994, "learning_rate": 6.2325666311420856e-06, "loss": 0.2186, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2534388178833587, "learning_rate": 6.1915995885650675e-06, "loss": 0.2295, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.24832088886769954, "learning_rate": 6.150742957589784e-06, "loss": 0.2111, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2577483613875329, "learning_rate": 6.109997064904774e-06, "loss": 0.2073, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.24936052709762294, "learning_rate": 6.069362236313092e-06, "loss": 0.2253, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2566806989920476, "learning_rate": 6.0288387967297565e-06, "loss": 0.2266, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2500205273695996, "learning_rate": 5.988427070179108e-06, "loss": 0.2421, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.25555994075264615, "learning_rate": 5.948127379792234e-06, "loss": 0.2208, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.2528350055096239, "learning_rate": 5.90794004780439e-06, "loss": 0.2256, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.2620713597610179, "learning_rate": 5.867865395552405e-06, "loss": 0.2166, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.24921496094657666, "learning_rate": 5.8279037434721364e-06, "loss": 0.2188, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.2453037037337074, "learning_rate": 5.788055411095892e-06, "loss": 0.2149, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2410824112838468, "learning_rate": 5.7483207170498625e-06, "loss": 0.2254, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.24605731315532783, "learning_rate": 5.708699979051613e-06, "loss": 0.2241, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2361362345665122, "learning_rate": 5.66919351390751e-06, "loss": 0.2267, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.24808252019926028, "learning_rate": 5.629801637510188e-06, "loss": 0.2074, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.25931276806888975, "learning_rate": 5.590524664836043e-06, "loss": 0.2359, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.24788594662666774, "learning_rate": 5.551362909942708e-06, "loss": 0.1913, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.24760732732772747, "learning_rate": 5.51231668596653e-06, "loss": 0.2186, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.23603353794815193, "learning_rate": 5.47338630512007e-06, "loss": 0.2108, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.2445981973026722, "learning_rate": 5.434572078689617e-06, "loss": 0.2268, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.23886614654249777, "learning_rate": 5.395874317032694e-06, "loss": 0.2363, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.24511796599549973, "learning_rate": 5.357293329575573e-06, "loss": 0.2164, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2575187049046286, "learning_rate": 5.318829424810797e-06, "loss": 0.2259, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.24740317059059572, "learning_rate": 5.280482910294728e-06, "loss": 0.218, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.23405024883808512, "learning_rate": 5.242254092645078e-06, "loss": 0.2054, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.24513703818368157, "learning_rate": 5.2041432775384445e-06, "loss": 0.1934, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.24395872535143182, "learning_rate": 5.166150769707892e-06, "loss": 0.2223, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.2533613495368633, "learning_rate": 5.128276872940503e-06, "loss": 0.193, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.24555866857951936, "learning_rate": 5.090521890074953e-06, "loss": 0.2322, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.25032894270918926, "learning_rate": 5.0528861229990675e-06, "loss": 0.2302, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.2697685046692483, "learning_rate": 5.015369872647442e-06, "loss": 0.1958, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2527255615293747, "learning_rate": 4.9779734389990195e-06, "loss": 0.2245, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.25703547798625836, "learning_rate": 4.940697121074675e-06, "loss": 0.2099, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.25894974249666414, "learning_rate": 4.903541216934864e-06, "loss": 0.2208, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.24292503513178393, "learning_rate": 4.8665060236772e-06, "loss": 0.2071, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2494357794262122, "learning_rate": 4.829591837434102e-06, "loss": 0.2171, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.2625522883505399, "learning_rate": 4.792798953370424e-06, "loss": 0.2064, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.24376797927012422, "learning_rate": 4.756127665681083e-06, "loss": 0.1953, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.24514756229798268, "learning_rate": 4.719578267588725e-06, "loss": 0.2227, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.2502033000961342, "learning_rate": 4.6831510513413525e-06, "loss": 0.2067, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3939293622815132, "learning_rate": 4.6468463082100176e-06, "loss": 0.1731, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.2993263033452937, "learning_rate": 4.610664328486485e-06, "loss": 0.1696, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.22491758724447303, "learning_rate": 4.5746054014809e-06, "loss": 0.2011, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.2547545236562663, "learning_rate": 4.5386698155194766e-06, "loss": 0.1738, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3442224957082091, "learning_rate": 4.502857857942204e-06, "loss": 0.1911, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3662253460591519, "learning_rate": 4.467169815100549e-06, "loss": 0.1737, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.27420937250371763, "learning_rate": 4.431605972355137e-06, "loss": 0.1625, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.2467073197157372, "learning_rate": 4.396166614073516e-06, "loss": 0.1664, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.2809680771526887, "learning_rate": 4.360852023627846e-06, "loss": 0.1619, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3403406645859998, "learning_rate": 4.325662483392656e-06, "loss": 0.1686, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2727214362663541, "learning_rate": 4.29059827474257e-06, "loss": 0.1705, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.23462616841346898, "learning_rate": 4.255659678050063e-06, "loss": 0.1811, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.23887623023215768, "learning_rate": 4.22084697268323e-06, "loss": 0.1727, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.26880904264567806, "learning_rate": 4.186160437003535e-06, "loss": 0.1769, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.3057824693904579, "learning_rate": 4.151600348363582e-06, "loss": 0.178, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.25058259456358856, "learning_rate": 4.11716698310493e-06, "loss": 0.1685, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.22748693018953, "learning_rate": 4.082860616555848e-06, "loss": 0.1565, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.23447949115765418, "learning_rate": 4.048681523029125e-06, "loss": 0.1857, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.23670977045993707, "learning_rate": 4.014629975819882e-06, "loss": 0.1411, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.2510532378103617, "learning_rate": 3.9807062472033855e-06, "loss": 0.2121, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.23737773749223026, "learning_rate": 3.94691060843287e-06, "loss": 0.1857, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.21426390065709558, "learning_rate": 3.913243329737353e-06, "loss": 0.1661, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.22512969438118854, "learning_rate": 3.879704680319503e-06, "loss": 0.179, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2424499869943827, "learning_rate": 3.846294928353471e-06, "loss": 0.1852, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.224565559142253, "learning_rate": 3.8130143409827345e-06, "loss": 0.1878, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.24237918801739325, "learning_rate": 3.7798631843179887e-06, "loss": 0.1729, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.22156290008649934, "learning_rate": 3.7468417234349973e-06, "loss": 0.1766, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.22074266097280976, "learning_rate": 3.7139502223724823e-06, "loss": 0.1789, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.21263954943303498, "learning_rate": 3.6811889441300095e-06, "loss": 0.1616, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2223420878291808, "learning_rate": 3.648558150665886e-06, "loss": 0.1895, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.21243969854740297, "learning_rate": 3.616058102895075e-06, "loss": 0.171, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.22586837265634258, "learning_rate": 3.583689060687079e-06, "loss": 0.1788, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.23133002238149933, "learning_rate": 3.5514512828639023e-06, "loss": 0.1667, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.2121392553721495, "learning_rate": 3.51934502719796e-06, "loss": 0.1814, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.22561197657748658, "learning_rate": 3.4873705504100185e-06, "loss": 0.2001, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.21259610054934044, "learning_rate": 3.4555281081671345e-06, "loss": 0.1807, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.2097309262235946, "learning_rate": 3.4238179550806326e-06, "loss": 0.1814, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.2081941468084881, "learning_rate": 3.3922403447040497e-06, "loss": 0.1648, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.21244437775102443, "learning_rate": 3.3607955295311247e-06, "loss": 0.1761, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.22274834067006122, "learning_rate": 3.32948376099375e-06, "loss": 0.182, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.20709849292918886, "learning_rate": 3.2983052894599976e-06, "loss": 0.1903, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.21895088016448663, "learning_rate": 3.2672603642320945e-06, "loss": 0.1865, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.21137308367277577, "learning_rate": 3.236349233544438e-06, "loss": 0.194, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.22296958850760423, "learning_rate": 3.205572144561604e-06, "loss": 0.1827, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2204776797378109, "learning_rate": 3.174929343376374e-06, "loss": 0.1706, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.22988161876261148, "learning_rate": 3.1444210750077777e-06, "loss": 0.1517, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2114018353337623, "learning_rate": 3.1140475833991046e-06, "loss": 0.1707, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.2239437907882552, "learning_rate": 3.0838091114159895e-06, "loss": 0.1548, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.21867544085292426, "learning_rate": 3.0537059008444524e-06, "loss": 0.1816, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.20895135217705424, "learning_rate": 3.0237381923889563e-06, "loss": 0.1727, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.211027153692451, "learning_rate": 2.9939062256704997e-06, "loss": 0.1719, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.2098435422077744, "learning_rate": 2.964210239224696e-06, "loss": 0.1787, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.2050399063861149, "learning_rate": 2.934650470499869e-06, "loss": 0.1924, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.23098681265163087, "learning_rate": 2.905227155855128e-06, "loss": 0.1913, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.21371167847783715, "learning_rate": 2.875940530558519e-06, "loss": 0.1496, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2056384496374333, "learning_rate": 2.8467908287851154e-06, "loss": 0.1752, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.21887449117934163, "learning_rate": 2.8177782836151603e-06, "loss": 0.1764, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.21754436884872108, "learning_rate": 2.7889031270321874e-06, "loss": 0.1839, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2146085435808605, "learning_rate": 2.760165589921184e-06, "loss": 0.1872, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.21716902004320332, "learning_rate": 2.7315659020667305e-06, "loss": 0.1861, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21418585899424358, "learning_rate": 2.703104292151164e-06, "loss": 0.188, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.21175815349486654, "learning_rate": 2.6747809877527607e-06, "loss": 0.1929, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.19746692381539405, "learning_rate": 2.6465962153439082e-06, "loss": 0.1736, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.22393882409955207, "learning_rate": 2.618550200289303e-06, "loss": 0.1529, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.20306118546872165, "learning_rate": 2.59064316684412e-06, "loss": 0.1648, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20398341472105644, "learning_rate": 2.562875338152264e-06, "loss": 0.1848, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2149900428508874, "learning_rate": 2.5352469362445552e-06, "loss": 0.155, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.21478109315268548, "learning_rate": 2.5077581820369523e-06, "loss": 0.1525, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.20984734506753697, "learning_rate": 2.480409295328803e-06, "loss": 0.1705, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.22095671548086981, "learning_rate": 2.45320049480108e-06, "loss": 0.2231, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.21620242313267515, "learning_rate": 2.4261319980146293e-06, "loss": 0.1779, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.23104951025274406, "learning_rate": 2.399204021408421e-06, "loss": 0.1701, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.20763392816426643, "learning_rate": 2.3724167802978395e-06, "loss": 0.1732, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.21446196962405903, "learning_rate": 2.3457704888729625e-06, "loss": 0.1808, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.19997381560771357, "learning_rate": 2.3192653601968162e-06, "loss": 0.172, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.21253709665936396, "learning_rate": 2.2929016062037057e-06, "loss": 0.1813, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.22918208767432038, "learning_rate": 2.2666794376975055e-06, "loss": 0.1735, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.21414369744750616, "learning_rate": 2.24059906434998e-06, "loss": 0.1829, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.20565545623383255, "learning_rate": 2.214660694699091e-06, "loss": 0.1543, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.21437111950458945, "learning_rate": 2.188864536147355e-06, "loss": 0.1729, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.22493490744609126, "learning_rate": 2.1632107949601757e-06, "loss": 0.167, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.21253298746900384, "learning_rate": 2.137699676264171e-06, "loss": 0.1826, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.21430649116396713, "learning_rate": 2.1123313840455738e-06, "loss": 0.175, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.19935599377290322, "learning_rate": 2.08710612114857e-06, "loss": 0.1741, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.20914008975966203, "learning_rate": 2.0620240892736953e-06, "loss": 0.1614, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.21542254280144438, "learning_rate": 2.0370854889762e-06, "loss": 0.1675, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.2009177313380078, "learning_rate": 2.0122905196644726e-06, "loss": 0.1738, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21431314728053227, "learning_rate": 1.987639379598427e-06, "loss": 0.1664, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21357036433104365, "learning_rate": 1.963132265887919e-06, "loss": 0.1645, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.2157589792481264, "learning_rate": 1.9387693744911784e-06, "loss": 0.1638, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.21337930521550033, "learning_rate": 1.9145509002132368e-06, "loss": 0.1742, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.22403031930688738, "learning_rate": 1.8904770367043723e-06, "loss": 0.2016, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.21330700055553725, "learning_rate": 1.8665479764585504e-06, "loss": 0.172, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.21127066830269992, "learning_rate": 1.8427639108118977e-06, "loss": 0.1804, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2123513790773402, "learning_rate": 1.8191250299411755e-06, "loss": 0.1839, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.21308869013328918, "learning_rate": 1.7956315228622446e-06, "loss": 0.1711, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2111161656685088, "learning_rate": 1.7722835774285553e-06, "loss": 0.1809, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.21031762861249995, "learning_rate": 1.7490813803296624e-06, "loss": 0.1753, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2183637289909382, "learning_rate": 1.726025117089718e-06, "loss": 0.1865, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.19642868828625837, "learning_rate": 1.70311497206598e-06, "loss": 0.1885, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2159722466440451, "learning_rate": 1.6803511284473638e-06, "loss": 0.1947, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.20599838883416127, "learning_rate": 1.6577337682529538e-06, "loss": 0.1864, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2041816132857468, "learning_rate": 1.6352630723305617e-06, "loss": 0.1845, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.20952697986043825, "learning_rate": 1.612939220355272e-06, "loss": 0.1789, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.2049753250078731, "learning_rate": 1.5907623908280112e-06, "loss": 0.1655, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.20386970144328193, "learning_rate": 1.568732761074121e-06, "loss": 0.1597, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.21327385534351823, "learning_rate": 1.5468505072419237e-06, "loss": 0.1771, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.2082230329738669, "learning_rate": 1.5251158043013448e-06, "loss": 0.1992, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2098002754510649, "learning_rate": 1.5035288260424885e-06, "loss": 0.1672, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.20574816217211553, "learning_rate": 1.4820897450742623e-06, "loss": 0.1699, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.21531617541956172, "learning_rate": 1.4607987328229767e-06, "loss": 0.1608, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.22423021288264364, "learning_rate": 1.4396559595310056e-06, "loss": 0.1607, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.21293484400522392, "learning_rate": 1.4186615942553973e-06, "loss": 0.1851, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.21381927781093213, "learning_rate": 1.3978158048665424e-06, "loss": 0.1684, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2116265899697268, "learning_rate": 1.3771187580468115e-06, "loss": 0.1995, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.20984569758183524, "learning_rate": 1.3565706192892392e-06, "loss": 0.1543, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.20816660094326275, "learning_rate": 1.3361715528961993e-06, "loss": 0.1642, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.21516212685505479, "learning_rate": 1.3159217219780817e-06, "loss": 0.1764, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.21185125617831016, "learning_rate": 1.2958212884519949e-06, "loss": 0.1808, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.20447922931442805, "learning_rate": 1.2758704130404675e-06, "loss": 0.16, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.21582302427722236, "learning_rate": 1.2560692552701738e-06, "loss": 0.17, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.21459813422709634, "learning_rate": 1.2364179734706382e-06, "loss": 0.1724, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.21689270852555143, "learning_rate": 1.2169167247729852e-06, "loss": 0.1892, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2117581300928947, "learning_rate": 1.1975656651086864e-06, "loss": 0.1633, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.20549581525400362, "learning_rate": 1.1783649492082926e-06, "loss": 0.1633, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.21745707794341138, "learning_rate": 1.1593147306002183e-06, "loss": 0.1661, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.20700734176313756, "learning_rate": 1.140415161609505e-06, "loss": 0.1854, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2117790436199651, "learning_rate": 1.121666393356604e-06, "loss": 0.1872, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.21238887250427627, "learning_rate": 1.1030685757561632e-06, "loss": 0.1639, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.20448167076848542, "learning_rate": 1.0846218575158373e-06, "loss": 0.1594, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.21802866041546393, "learning_rate": 1.066326386135097e-06, "loss": 0.1953, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.20772381401604645, "learning_rate": 1.0481823079040398e-06, "loss": 0.1687, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.21740072007007014, "learning_rate": 1.0301897679022344e-06, "loss": 0.1667, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.225792233103542, "learning_rate": 1.0123489099975491e-06, "loss": 0.1725, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.21427805101446354, "learning_rate": 9.9465987684501e-07, "loss": 0.1828, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.20633400387506834, "learning_rate": 9.771228098856534e-07, "loss": 0.173, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.2125145170704245, "learning_rate": 9.597378493454013e-07, "loss": 0.1772, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.20504483270717627, "learning_rate": 9.425051342339353e-07, "loss": 0.1708, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.21064477697963863, "learning_rate": 9.254248023435864e-07, "loss": 0.1721, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.20949445095414818, "learning_rate": 9.084969902482288e-07, "loss": 0.1688, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.3846563954913059, "learning_rate": 8.917218333021993e-07, "loss": 0.1737, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2086012607142434, "learning_rate": 8.750994656392109e-07, "loss": 0.1665, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.20406725773231021, "learning_rate": 8.58630020171265e-07, "loss": 0.1644, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.20884331785211752, "learning_rate": 8.423136285876099e-07, "loss": 0.1665, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2019394441720554, "learning_rate": 8.26150421353682e-07, "loss": 0.1966, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2154396371979417, "learning_rate": 8.101405277100549e-07, "loss": 0.1793, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2236767924436953, "learning_rate": 7.942840756714077e-07, "loss": 0.1446, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.21382239968192343, "learning_rate": 7.785811920255093e-07, "loss": 0.1667, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.22545992680446275, "learning_rate": 7.630320023322024e-07, "loss": 0.1729, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.20163982429786506, "learning_rate": 7.476366309223903e-07, "loss": 0.1535, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.21575481717816497, "learning_rate": 7.323952008970537e-07, "loss": 0.1734, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.20800471760485287, "learning_rate": 7.173078341262618e-07, "loss": 0.1732, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.20151936734143933, "learning_rate": 7.023746512481989e-07, "loss": 0.168, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.21010993583926232, "learning_rate": 6.875957716681902e-07, "loss": 0.1673, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.20763838996451145, "learning_rate": 6.729713135577687e-07, "loss": 0.2046, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.21150726478133428, "learning_rate": 6.585013938537143e-07, "loss": 0.1964, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2186255949060111, "learning_rate": 6.441861282571115e-07, "loss": 0.1529, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.20246404165267545, "learning_rate": 6.300256312324471e-07, "loss": 0.175, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.20884591644518408, "learning_rate": 6.160200160066776e-07, "loss": 0.1725, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.20644658793011159, "learning_rate": 6.021693945683327e-07, "loss": 0.159, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.20005264037858436, "learning_rate": 5.884738776666044e-07, "loss": 0.1712, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.21085707674693838, "learning_rate": 5.749335748104878e-07, "loss": 0.1748, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.20511658599075208, "learning_rate": 5.615485942678778e-07, "loss": 0.1831, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.21478097361830048, "learning_rate": 5.483190430647289e-07, "loss": 0.1782, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.20711028598292, "learning_rate": 5.352450269841747e-07, "loss": 0.1638, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.21343348043020396, "learning_rate": 5.22326650565701e-07, "loss": 0.1919, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.20145390665261084, "learning_rate": 5.095640171043048e-07, "loss": 0.1492, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.21001805351807368, "learning_rate": 4.969572286496594e-07, "loss": 0.179, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.21448344766688235, "learning_rate": 4.845063860053079e-07, "loss": 0.164, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.20852900535431868, "learning_rate": 4.7221158872785997e-07, "loss": 0.1685, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.19685701467339284, "learning_rate": 4.600729351261857e-07, "loss": 0.1791, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.20944763868087746, "learning_rate": 4.4809052226063355e-07, "loss": 0.19, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.2096558849563074, "learning_rate": 4.3626444594226046e-07, "loss": 0.1911, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.21120549673290948, "learning_rate": 4.245948007320588e-07, "loss": 0.1765, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.2132430417163358, "learning_rate": 4.130816799401971e-07, "loss": 0.1718, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.21307339979199152, "learning_rate": 4.017251756252827e-07, "loss": 0.1725, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.20333980292582535, "learning_rate": 3.9052537859362473e-07, "loss": 0.1927, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.21353226127655012, "learning_rate": 3.7948237839849687e-07, "loss": 0.1981, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.2052867215782759, "learning_rate": 3.6859626333943797e-07, "loss": 0.179, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.21628845994611134, "learning_rate": 3.578671204615347e-07, "loss": 0.1814, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.21261492510238345, "learning_rate": 3.472950355547267e-07, "loss": 0.1657, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.1992515374606408, "learning_rate": 3.3688009315312244e-07, "loss": 0.1725, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2110618147750916, "learning_rate": 3.266223765343224e-07, "loss": 0.1526, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2099560861740066, "learning_rate": 3.16521967718757e-07, "loss": 0.1693, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.20493366622045392, "learning_rate": 3.0657894746902726e-07, "loss": 0.1732, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.202212810248431, "learning_rate": 2.9679339528925654e-07, "loss": 0.155, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.20273638733219934, "learning_rate": 2.871653894244597e-07, "loss": 0.1794, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.20536748677739933, "learning_rate": 2.7769500685991266e-07, "loss": 0.1985, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.20779109459299103, "learning_rate": 2.683823233205485e-07, "loss": 0.182, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.20537015805016992, "learning_rate": 2.592274132703287e-07, "loss": 0.1849, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.21000240162519518, "learning_rate": 2.502303499116754e-07, "loss": 0.1785, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.21072538966540877, "learning_rate": 2.413912051848666e-07, "loss": 0.172, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.20581179548316, "learning_rate": 2.3271004976746613e-07, "loss": 0.1778, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.20385068343809418, "learning_rate": 2.2418695307376393e-07, "loss": 0.1806, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.19878164820338254, "learning_rate": 2.1582198325420968e-07, "loss": 0.1819, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.19932941859810702, "learning_rate": 2.0761520719488447e-07, "loss": 0.1982, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.1981629458846275, "learning_rate": 1.9956669051694798e-07, "loss": 0.1685, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.2073291348535938, "learning_rate": 1.916764975761254e-07, "loss": 0.1821, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.21253925346777772, "learning_rate": 1.839446914621923e-07, "loss": 0.1807, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.20964884894855954, "learning_rate": 1.7637133399845962e-07, "loss": 0.1716, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.21471299344050626, "learning_rate": 1.6895648574129397e-07, "loss": 0.1542, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2061512550255899, "learning_rate": 1.6170020597962465e-07, "loss": 0.1857, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.20909823050445936, "learning_rate": 1.5460255273447078e-07, "loss": 0.169, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.20946573723273956, "learning_rate": 1.4766358275847715e-07, "loss": 0.1783, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.20746583774952881, "learning_rate": 1.4088335153546573e-07, "loss": 0.1743, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.21237479637342688, "learning_rate": 1.3426191327998496e-07, "loss": 0.1948, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.20741914597318695, "learning_rate": 1.277993209368744e-07, "loss": 0.1688, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.20780501385263137, "learning_rate": 1.214956261808542e-07, "loss": 0.1622, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.21543654173311969, "learning_rate": 1.1535087941609846e-07, "loss": 0.1841, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.21406411059436878, "learning_rate": 1.0936512977583802e-07, "loss": 0.1977, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.20673066924671718, "learning_rate": 1.0353842512196732e-07, "loss": 0.1845, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.21041026706626745, "learning_rate": 9.787081204466253e-08, "loss": 0.1555, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.210778944935336, "learning_rate": 9.236233586200627e-08, "loss": 0.1909, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2089876126963992, "learning_rate": 8.70130406196279e-08, "loss": 0.1888, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.21013394343579506, "learning_rate": 8.182296909035047e-08, "loss": 0.1766, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.19318379741490216, "learning_rate": 7.679216277384439e-08, "loss": 0.1719, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2089608020716662, "learning_rate": 7.19206618963053e-08, "loss": 0.1728, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.20329965099583644, "learning_rate": 6.720850541012347e-08, "loss": 0.1849, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.20578156476814893, "learning_rate": 6.265573099357714e-08, "loss": 0.1574, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.20878257599615646, "learning_rate": 5.826237505053067e-08, "loss": 0.1735, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.22021388775712936, "learning_rate": 5.4028472710137e-08, "loss": 0.1494, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.2184277216776276, "learning_rate": 4.9954057826571146e-08, "loss": 0.161, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2115650625540677, "learning_rate": 4.6039162978743776e-08, "loss": 0.1548, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.20526719666187052, "learning_rate": 4.228381947004812e-08, "loss": 0.1661, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.2046468399337856, "learning_rate": 3.868805732811343e-08, "loss": 0.1701, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.21393948869616494, "learning_rate": 3.525190530455636e-08, "loss": 0.1862, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.21413622773513186, "learning_rate": 3.197539087475887e-08, "loss": 0.1733, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.20337051499184836, "learning_rate": 2.8858540237641786e-08, "loss": 0.1739, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.21427181486556154, "learning_rate": 2.5901378315458247e-08, "loss": 0.1515, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.20495148396901974, "learning_rate": 2.3103928753598347e-08, "loss": 0.1672, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.20875608138859023, "learning_rate": 2.0466213920393718e-08, "loss": 0.1795, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.20630426566015672, "learning_rate": 1.7988254906942115e-08, "loss": 0.172, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.20529333606815345, "learning_rate": 1.5670071526936447e-08, "loss": 0.1403, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.21744459767527316, "learning_rate": 1.3511682316509344e-08, "loss": 0.1875, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.20722771261907277, "learning_rate": 1.1513104534086605e-08, "loss": 0.1915, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.1965510106585952, "learning_rate": 9.67435416023843e-09, "loss": 0.1645, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.21670979056590584, "learning_rate": 7.995445897566178e-09, "loss": 0.1651, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.20496977307743938, "learning_rate": 6.476393170578021e-09, "loss": 0.1588, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.21506616116598834, "learning_rate": 5.11720812557348e-09, "loss": 0.1501, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.2160745475477599, "learning_rate": 3.917901630563492e-09, "loss": 0.1647, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.21163773229846713, "learning_rate": 2.878483275170485e-09, "loss": 0.1773, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.210558705528482, "learning_rate": 1.998961370555108e-09, "loss": 0.1857, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.20822131963666665, "learning_rate": 1.2793429493518361e-09, "loss": 0.1637, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2047186705172419, "learning_rate": 7.196337656112384e-10, "loss": 0.1759, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.206017284044567, "learning_rate": 3.198382947511292e-10, "loss": 0.1724, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.20715298093442236, "learning_rate": 7.995973352770137e-11, "loss": 0.1885, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.1916160028285681, "learning_rate": 0.0, "loss": 0.1579, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 2.6027063082850714e+18, "train_loss": 0.32658012527444585, "train_runtime": 25714.1921, "train_samples_per_second": 6.144, "train_steps_per_second": 0.048 } ], "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": 2.6027063082850714e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }