{ "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": 6.7470303796470645, "learning_rate": 3.2258064516129035e-07, "loss": 0.8771, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.685946722765869, "learning_rate": 6.451612903225807e-07, "loss": 0.8886, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.121067194222797, "learning_rate": 9.67741935483871e-07, "loss": 0.8926, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.65552616204629, "learning_rate": 1.2903225806451614e-06, "loss": 0.8673, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.790530064783211, "learning_rate": 1.6129032258064516e-06, "loss": 0.8773, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.167643437613419, "learning_rate": 1.935483870967742e-06, "loss": 0.8598, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.389444301272644, "learning_rate": 2.2580645161290324e-06, "loss": 0.8572, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.883645410189767, "learning_rate": 2.580645161290323e-06, "loss": 0.8463, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.935063327079886, "learning_rate": 2.903225806451613e-06, "loss": 0.7349, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.7066928620672464, "learning_rate": 3.225806451612903e-06, "loss": 0.7808, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.352635397024672, "learning_rate": 3.548387096774194e-06, "loss": 0.7556, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.454950174945768, "learning_rate": 3.870967741935484e-06, "loss": 0.7176, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.954702411074296, "learning_rate": 4.193548387096774e-06, "loss": 0.7324, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.656748011790387, "learning_rate": 4.516129032258065e-06, "loss": 0.7176, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.4156299520844873, "learning_rate": 4.838709677419355e-06, "loss": 0.7053, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.72993967956337, "learning_rate": 5.161290322580646e-06, "loss": 0.6555, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.434910065464178, "learning_rate": 5.483870967741935e-06, "loss": 0.5867, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.3619183545279947, "learning_rate": 5.806451612903226e-06, "loss": 0.6396, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.8293498131358503, "learning_rate": 6.129032258064517e-06, "loss": 0.6163, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.5347703700883224, "learning_rate": 6.451612903225806e-06, "loss": 0.6176, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.4320315356441715, "learning_rate": 6.774193548387097e-06, "loss": 0.5934, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.7947028994559333, "learning_rate": 7.096774193548388e-06, "loss": 0.6121, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.7721248047025147, "learning_rate": 7.4193548387096784e-06, "loss": 0.6119, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.3072213017703047, "learning_rate": 7.741935483870968e-06, "loss": 0.5874, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8725956848540609, "learning_rate": 8.064516129032258e-06, "loss": 0.5666, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.0514804977902616, "learning_rate": 8.387096774193549e-06, "loss": 0.5499, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.2142551708563163, "learning_rate": 8.70967741935484e-06, "loss": 0.5427, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8324004820801881, "learning_rate": 9.03225806451613e-06, "loss": 0.5783, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.762085138550744, "learning_rate": 9.35483870967742e-06, "loss": 0.5572, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.925278469851166, "learning_rate": 9.67741935483871e-06, "loss": 0.5573, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.7840248216916033, "learning_rate": 1e-05, "loss": 0.5346, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7004338057311451, "learning_rate": 1.0322580645161291e-05, "loss": 0.5309, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6227873493205804, "learning_rate": 1.0645161290322582e-05, "loss": 0.541, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7204987207759159, "learning_rate": 1.096774193548387e-05, "loss": 0.5286, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.7464497478972382, "learning_rate": 1.1290322580645164e-05, "loss": 0.4995, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6284682885371767, "learning_rate": 1.1612903225806453e-05, "loss": 0.5436, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5938023671713929, "learning_rate": 1.1935483870967743e-05, "loss": 0.5203, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6064406459261241, "learning_rate": 1.2258064516129034e-05, "loss": 0.5129, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.69470541663559, "learning_rate": 1.2580645161290324e-05, "loss": 0.4788, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6054680386566196, "learning_rate": 1.2903225806451613e-05, "loss": 0.5, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 1.3256724985991823, "learning_rate": 1.3225806451612903e-05, "loss": 0.5523, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6346765785923706, "learning_rate": 1.3548387096774194e-05, "loss": 0.5126, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5292056566024401, "learning_rate": 1.3870967741935486e-05, "loss": 0.5203, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5471527543163095, "learning_rate": 1.4193548387096776e-05, "loss": 0.4867, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.7095525074615093, "learning_rate": 1.4516129032258066e-05, "loss": 0.5108, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5427549292149881, "learning_rate": 1.4838709677419357e-05, "loss": 0.4925, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.6105107261627384, "learning_rate": 1.5161290322580646e-05, "loss": 0.5005, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.6796294574933602, "learning_rate": 1.5483870967741936e-05, "loss": 0.5034, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6880108628604786, "learning_rate": 1.5806451612903226e-05, "loss": 0.4986, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.5875737955575938, "learning_rate": 1.6129032258064517e-05, "loss": 0.4932, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5754442085034163, "learning_rate": 1.6451612903225807e-05, "loss": 0.5223, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.6341411803410131, "learning_rate": 1.6774193548387098e-05, "loss": 0.5127, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.5915723827506647, "learning_rate": 1.7096774193548388e-05, "loss": 0.5148, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.6003316536489752, "learning_rate": 1.741935483870968e-05, "loss": 0.5027, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.5568996744540395, "learning_rate": 1.774193548387097e-05, "loss": 0.5243, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6072782724203101, "learning_rate": 1.806451612903226e-05, "loss": 0.4963, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.5304675605642182, "learning_rate": 1.838709677419355e-05, "loss": 0.4849, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6105587741368335, "learning_rate": 1.870967741935484e-05, "loss": 0.5053, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5545517247337485, "learning_rate": 1.903225806451613e-05, "loss": 0.4921, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.55761152959285, "learning_rate": 1.935483870967742e-05, "loss": 0.5096, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5522991698834697, "learning_rate": 1.967741935483871e-05, "loss": 0.5015, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.589339667542492, "learning_rate": 2e-05, "loss": 0.476, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5511507527595685, "learning_rate": 2.0322580645161292e-05, "loss": 0.4798, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.5675184142691636, "learning_rate": 2.0645161290322582e-05, "loss": 0.464, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.6070274082188558, "learning_rate": 2.0967741935483873e-05, "loss": 0.4785, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6892546786615927, "learning_rate": 2.1290322580645163e-05, "loss": 0.4873, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.6253029013623833, "learning_rate": 2.161290322580645e-05, "loss": 0.488, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.7118946860519892, "learning_rate": 2.193548387096774e-05, "loss": 0.5082, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.6701264179708222, "learning_rate": 2.225806451612903e-05, "loss": 0.4879, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.7583819682977626, "learning_rate": 2.2580645161290328e-05, "loss": 0.4875, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7346434061700245, "learning_rate": 2.2903225806451615e-05, "loss": 0.4861, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.6541509271570677, "learning_rate": 2.3225806451612906e-05, "loss": 0.4894, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.7317617100352355, "learning_rate": 2.3548387096774196e-05, "loss": 0.4807, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.7929985543247112, "learning_rate": 2.3870967741935486e-05, "loss": 0.4951, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.5810353389910436, "learning_rate": 2.4193548387096777e-05, "loss": 0.4871, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.7649877278867576, "learning_rate": 2.4516129032258067e-05, "loss": 0.4804, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.6909791393906455, "learning_rate": 2.4838709677419358e-05, "loss": 0.4588, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7531844641040711, "learning_rate": 2.5161290322580648e-05, "loss": 0.4825, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8010121372806309, "learning_rate": 2.548387096774194e-05, "loss": 0.511, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.6520086388529319, "learning_rate": 2.5806451612903226e-05, "loss": 0.4814, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.9734290647851683, "learning_rate": 2.6129032258064516e-05, "loss": 0.4766, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.550022397902631, "learning_rate": 2.6451612903225806e-05, "loss": 0.4618, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8993718078287011, "learning_rate": 2.6774193548387097e-05, "loss": 0.4999, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.6800410464791209, "learning_rate": 2.7096774193548387e-05, "loss": 0.4522, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.5918007215948169, "learning_rate": 2.7419354838709678e-05, "loss": 0.4897, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.6886052811043515, "learning_rate": 2.774193548387097e-05, "loss": 0.4947, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.6034566016218327, "learning_rate": 2.8064516129032262e-05, "loss": 0.488, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.696071711804453, "learning_rate": 2.8387096774193552e-05, "loss": 0.4984, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.6480526458534751, "learning_rate": 2.8709677419354843e-05, "loss": 0.462, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.6577331508073644, "learning_rate": 2.9032258064516133e-05, "loss": 0.4799, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.7014393327808875, "learning_rate": 2.9354838709677423e-05, "loss": 0.4857, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.6394226426311717, "learning_rate": 2.9677419354838714e-05, "loss": 0.4871, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.8051991363494596, "learning_rate": 3.0000000000000004e-05, "loss": 0.4851, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.5651764820739398, "learning_rate": 3.032258064516129e-05, "loss": 0.4931, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.9171532616524023, "learning_rate": 3.0645161290322585e-05, "loss": 0.4738, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.7770651507205117, "learning_rate": 3.096774193548387e-05, "loss": 0.4494, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.7113680478654619, "learning_rate": 3.1290322580645166e-05, "loss": 0.4906, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.7226323458442674, "learning_rate": 3.161290322580645e-05, "loss": 0.4756, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.6969693320377103, "learning_rate": 3.193548387096774e-05, "loss": 0.5078, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.9225975269395519, "learning_rate": 3.2258064516129034e-05, "loss": 0.4781, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.667123245007525, "learning_rate": 3.258064516129033e-05, "loss": 0.47, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.7599212706439887, "learning_rate": 3.2903225806451614e-05, "loss": 0.4658, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.6122467410556874, "learning_rate": 3.322580645161291e-05, "loss": 0.4804, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.7439092396551054, "learning_rate": 3.3548387096774195e-05, "loss": 0.4809, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.6843577046370687, "learning_rate": 3.387096774193549e-05, "loss": 0.4684, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.8963247007778226, "learning_rate": 3.4193548387096776e-05, "loss": 0.4512, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.8963216342612377, "learning_rate": 3.451612903225807e-05, "loss": 0.4931, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.6521382664941999, "learning_rate": 3.483870967741936e-05, "loss": 0.4752, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.8693808547671965, "learning_rate": 3.516129032258065e-05, "loss": 0.4716, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.6107435705686474, "learning_rate": 3.548387096774194e-05, "loss": 0.483, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.731311333807072, "learning_rate": 3.5806451612903225e-05, "loss": 0.4605, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.709758813863349, "learning_rate": 3.612903225806452e-05, "loss": 0.5072, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.6768589944058252, "learning_rate": 3.6451612903225805e-05, "loss": 0.4803, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.7612574779286965, "learning_rate": 3.67741935483871e-05, "loss": 0.4661, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.6855101264556199, "learning_rate": 3.7096774193548386e-05, "loss": 0.4803, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6601658987537004, "learning_rate": 3.741935483870968e-05, "loss": 0.4979, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.6233205089923938, "learning_rate": 3.7741935483870974e-05, "loss": 0.4917, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.6122691012426453, "learning_rate": 3.806451612903226e-05, "loss": 0.4808, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.6419746961273045, "learning_rate": 3.8387096774193555e-05, "loss": 0.4617, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.6351242824027538, "learning_rate": 3.870967741935484e-05, "loss": 0.4771, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.7358193215660858, "learning_rate": 3.9032258064516135e-05, "loss": 0.5214, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6758398486103905, "learning_rate": 3.935483870967742e-05, "loss": 0.4956, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.6893973943623894, "learning_rate": 3.9677419354838716e-05, "loss": 0.4711, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.6207941112670615, "learning_rate": 4e-05, "loss": 0.4678, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.6799725679063647, "learning_rate": 3.9999920040266474e-05, "loss": 0.4719, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.9261167111870067, "learning_rate": 3.999968016170525e-05, "loss": 0.5021, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.7737883128716261, "learning_rate": 3.9999280366234394e-05, "loss": 0.4699, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.6707243674030359, "learning_rate": 3.999872065705065e-05, "loss": 0.4956, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.58426163778175, "learning_rate": 3.999800103862945e-05, "loss": 0.5043, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.5657644738514606, "learning_rate": 3.9997121516724834e-05, "loss": 0.5037, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.6089076988915663, "learning_rate": 3.999608209836944e-05, "loss": 0.4739, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.5569161949650722, "learning_rate": 3.999488279187443e-05, "loss": 0.4864, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.6028381302869301, "learning_rate": 3.9993523606829425e-05, "loss": 0.4792, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.588734458936196, "learning_rate": 3.9992004554102435e-05, "loss": 0.4852, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.6066464355612768, "learning_rate": 3.999032564583976e-05, "loss": 0.5092, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.619141086951969, "learning_rate": 3.998848689546591e-05, "loss": 0.4636, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.5741101974161477, "learning_rate": 3.9986488317683496e-05, "loss": 0.4734, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.4954497172808242, "learning_rate": 3.9984329928473067e-05, "loss": 0.4707, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.5730977527083592, "learning_rate": 3.998201174509306e-05, "loss": 0.4888, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.5233691687157386, "learning_rate": 3.997953378607961e-05, "loss": 0.4361, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6991221801796128, "learning_rate": 3.9976896071246403e-05, "loss": 0.4878, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.5496666658066727, "learning_rate": 3.997409862168454e-05, "loss": 0.4749, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.6459507393990593, "learning_rate": 3.997114145976237e-05, "loss": 0.4851, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5582181715932969, "learning_rate": 3.9968024609125245e-05, "loss": 0.4906, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.5965126810424491, "learning_rate": 3.996474809469545e-05, "loss": 0.4617, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.5619604129246498, "learning_rate": 3.996131194267189e-05, "loss": 0.4508, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.6453408362764159, "learning_rate": 3.995771618052995e-05, "loss": 0.4936, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.6082757490163857, "learning_rate": 3.9953960837021256e-05, "loss": 0.4758, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.5699692546092723, "learning_rate": 3.995004594217343e-05, "loss": 0.4585, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6838286766487978, "learning_rate": 3.994597152728987e-05, "loss": 0.4812, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.5294579359989837, "learning_rate": 3.994173762494947e-05, "loss": 0.4619, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.7121473062150809, "learning_rate": 3.9937344269006424e-05, "loss": 0.4605, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.5597017387182531, "learning_rate": 3.993279149458988e-05, "loss": 0.4804, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.7085334659237751, "learning_rate": 3.9928079338103695e-05, "loss": 0.4972, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.7876207328969511, "learning_rate": 3.992320783722616e-05, "loss": 0.4879, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.8036701555318885, "learning_rate": 3.991817703090965e-05, "loss": 0.4858, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.7962688068924466, "learning_rate": 3.991298695938038e-05, "loss": 0.4642, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6888974399854357, "learning_rate": 3.9907637664138e-05, "loss": 0.4684, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7425094228322069, "learning_rate": 3.990212918795534e-05, "loss": 0.4537, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.5632709869651245, "learning_rate": 3.9896461574878036e-05, "loss": 0.4986, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6408931785306358, "learning_rate": 3.989063487022416e-05, "loss": 0.4912, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.49999156859473337, "learning_rate": 3.9884649120583903e-05, "loss": 0.4736, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5554372391529164, "learning_rate": 3.987850437381915e-05, "loss": 0.469, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.5387087400533929, "learning_rate": 3.987220067906313e-05, "loss": 0.4878, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.5391999930239315, "learning_rate": 3.986573808672002e-05, "loss": 0.4894, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.4962743501161268, "learning_rate": 3.9859116648464534e-05, "loss": 0.5248, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5454182873021556, "learning_rate": 3.985233641724152e-05, "loss": 0.4618, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.5024578547635304, "learning_rate": 3.984539744726554e-05, "loss": 0.4657, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6322447753900245, "learning_rate": 3.983829979402038e-05, "loss": 0.4809, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.5071149912547784, "learning_rate": 3.983104351425871e-05, "loss": 0.4999, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.5585836384483638, "learning_rate": 3.982362866600154e-05, "loss": 0.4363, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.5863978754413792, "learning_rate": 3.9816055308537806e-05, "loss": 0.476, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.6310760081722712, "learning_rate": 3.980832350242388e-05, "loss": 0.4831, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5824138006974983, "learning_rate": 3.980043330948306e-05, "loss": 0.4567, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.5766632522074432, "learning_rate": 3.9792384792805124e-05, "loss": 0.4806, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.6327153895445515, "learning_rate": 3.978417801674579e-05, "loss": 0.4523, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.6115358438822888, "learning_rate": 3.9775813046926244e-05, "loss": 0.4738, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5297791251133845, "learning_rate": 3.976728995023254e-05, "loss": 0.4556, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.5821292889308237, "learning_rate": 3.975860879481514e-05, "loss": 0.4673, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.4873270973739064, "learning_rate": 3.974976965008833e-05, "loss": 0.4754, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5390145581260386, "learning_rate": 3.9740772586729674e-05, "loss": 0.438, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.6053017186465229, "learning_rate": 3.973161767667946e-05, "loss": 0.4748, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6376504416865751, "learning_rate": 3.972230499314009e-05, "loss": 0.4845, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.5391689079749915, "learning_rate": 3.9712834610575545e-05, "loss": 0.4831, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5888556309083675, "learning_rate": 3.9703206604710746e-05, "loss": 0.5053, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.5935604566208559, "learning_rate": 3.969342105253098e-05, "loss": 0.4958, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.5334202216427546, "learning_rate": 3.9683478032281246e-05, "loss": 0.4743, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5563358137450829, "learning_rate": 3.967337762346568e-05, "loss": 0.4884, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.621332205374585, "learning_rate": 3.9663119906846885e-05, "loss": 0.5048, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.49573959025390024, "learning_rate": 3.965270496444528e-05, "loss": 0.4861, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.5789000802905325, "learning_rate": 3.9642132879538465e-05, "loss": 0.4724, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5259237604903749, "learning_rate": 3.9631403736660566e-05, "loss": 0.4329, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5002154642047913, "learning_rate": 3.962051762160151e-05, "loss": 0.5009, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.5383709119803212, "learning_rate": 3.960947462140638e-05, "loss": 0.5011, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.4223846861344007, "learning_rate": 3.959827482437472e-05, "loss": 0.4595, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.5858779002384994, "learning_rate": 3.958691832005981e-05, "loss": 0.4726, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5449208560931933, "learning_rate": 3.9575405199267944e-05, "loss": 0.4893, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.5017158309691315, "learning_rate": 3.956373555405774e-05, "loss": 0.5086, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.5455057477137064, "learning_rate": 3.955190947773937e-05, "loss": 0.4821, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.44077393606890564, "learning_rate": 3.9539927064873824e-05, "loss": 0.4496, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.5952092258537315, "learning_rate": 3.952778841127214e-05, "loss": 0.4519, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.4779908098899198, "learning_rate": 3.95154936139947e-05, "loss": 0.4553, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5839522480491026, "learning_rate": 3.950304277135034e-05, "loss": 0.4611, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.48629877853699344, "learning_rate": 3.94904359828957e-05, "loss": 0.4678, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5043540334975097, "learning_rate": 3.94776733494343e-05, "loss": 0.4579, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.46963746793246947, "learning_rate": 3.9464754973015826e-05, "loss": 0.4518, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.4920469941919182, "learning_rate": 3.9451680956935275e-05, "loss": 0.4438, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5271239195802873, "learning_rate": 3.943845140573213e-05, "loss": 0.5139, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.5078283711208046, "learning_rate": 3.942506642518952e-05, "loss": 0.4509, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.50071763366846, "learning_rate": 3.9411526122333396e-05, "loss": 0.4579, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.4507442633385743, "learning_rate": 3.939783060543167e-05, "loss": 0.4478, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5361389694960479, "learning_rate": 3.938397998399333e-05, "loss": 0.4612, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.44725759847684093, "learning_rate": 3.936997436876756e-05, "loss": 0.4549, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.5768394810137517, "learning_rate": 3.935581387174289e-05, "loss": 0.4509, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5461436342832768, "learning_rate": 3.9341498606146295e-05, "loss": 0.4665, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.4905285338521534, "learning_rate": 3.932702868644224e-05, "loss": 0.459, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.6665748504357397, "learning_rate": 3.931240422833181e-05, "loss": 0.5173, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5338421133411398, "learning_rate": 3.9297625348751806e-05, "loss": 0.4352, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5519478293287565, "learning_rate": 3.9282692165873744e-05, "loss": 0.4712, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.5005815408258227, "learning_rate": 3.9267604799102945e-05, "loss": 0.4647, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.45601048920628434, "learning_rate": 3.9252363369077615e-05, "loss": 0.4851, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5698006910188853, "learning_rate": 3.9236967997667796e-05, "loss": 0.4917, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.49416361084985855, "learning_rate": 3.9221418807974496e-05, "loss": 0.4637, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5233504604018684, "learning_rate": 3.92057159243286e-05, "loss": 0.4594, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.5147562241366659, "learning_rate": 3.9189859472289956e-05, "loss": 0.4738, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.4725572335929975, "learning_rate": 3.9173849578646324e-05, "loss": 0.4843, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.4828916374252631, "learning_rate": 3.9157686371412395e-05, "loss": 0.4562, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.4431508032488207, "learning_rate": 3.914136997982874e-05, "loss": 0.4807, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.44555105343823775, "learning_rate": 3.912490053436079e-05, "loss": 0.4333, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.4630290168525961, "learning_rate": 3.9108278166697805e-05, "loss": 0.4859, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.44397015469541035, "learning_rate": 3.909150300975178e-05, "loss": 0.4621, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4848074028975475, "learning_rate": 3.907457519765642e-05, "loss": 0.4547, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.4740987923457724, "learning_rate": 3.905749486576607e-05, "loss": 0.4766, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.47504904752924615, "learning_rate": 3.90402621506546e-05, "loss": 0.4803, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5051159262818816, "learning_rate": 3.902287719011435e-05, "loss": 0.4648, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.4878220936278041, "learning_rate": 3.900534012315499e-05, "loss": 0.4698, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.6220808260790486, "learning_rate": 3.8987651090002454e-05, "loss": 0.4647, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.4743861248668169, "learning_rate": 3.896981023209777e-05, "loss": 0.4697, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4826209250337515, "learning_rate": 3.8951817692095966e-05, "loss": 0.4471, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5338374207303727, "learning_rate": 3.893367361386491e-05, "loss": 0.4702, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4789452095082636, "learning_rate": 3.891537814248417e-05, "loss": 0.4562, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4985964034520127, "learning_rate": 3.889693142424384e-05, "loss": 0.4443, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5125977772761038, "learning_rate": 3.8878333606643405e-05, "loss": 0.4536, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.5169885766662672, "learning_rate": 3.885958483839049e-05, "loss": 0.4619, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.5010961711249358, "learning_rate": 3.8840685269399786e-05, "loss": 0.4338, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.5082834488750215, "learning_rate": 3.882163505079171e-05, "loss": 0.4803, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5370305101003974, "learning_rate": 3.880243433489132e-05, "loss": 0.4767, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.6392391878970675, "learning_rate": 3.878308327522702e-05, "loss": 0.4009, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.539703585759448, "learning_rate": 3.876358202652936e-05, "loss": 0.4082, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.6051375504121111, "learning_rate": 3.8743930744729835e-05, "loss": 0.384, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.5599055959782032, "learning_rate": 3.8724129586959535e-05, "loss": 0.3731, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.49118354581525586, "learning_rate": 3.870417871154801e-05, "loss": 0.3772, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6518141096826957, "learning_rate": 3.868407827802192e-05, "loss": 0.3322, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.46607523653578425, "learning_rate": 3.8663828447103804e-05, "loss": 0.3598, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.515358078941688, "learning_rate": 3.8643429380710765e-05, "loss": 0.3743, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5855541695241459, "learning_rate": 3.862288124195319e-05, "loss": 0.3697, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.5150004417583267, "learning_rate": 3.8602184195133464e-05, "loss": 0.3677, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5159700266472309, "learning_rate": 3.8581338405744604e-05, "loss": 0.3575, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.4981672772704698, "learning_rate": 3.8560344040468996e-05, "loss": 0.3857, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.48082590092151184, "learning_rate": 3.853920126717703e-05, "loss": 0.3634, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.4957983059308575, "learning_rate": 3.851791025492574e-05, "loss": 0.3505, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.4880241617482965, "learning_rate": 3.8496471173957515e-05, "loss": 0.3628, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.48392378878900305, "learning_rate": 3.847488419569866e-05, "loss": 0.3676, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5438971202629486, "learning_rate": 3.8453149492758077e-05, "loss": 0.3501, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.4398864612430835, "learning_rate": 3.8431267238925886e-05, "loss": 0.3531, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5186262789937728, "learning_rate": 3.840923760917199e-05, "loss": 0.3874, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.47994282973102104, "learning_rate": 3.838706077964473e-05, "loss": 0.3641, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.48277272824948264, "learning_rate": 3.836473692766944e-05, "loss": 0.3636, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5132814320454341, "learning_rate": 3.834226623174705e-05, "loss": 0.3688, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.49347803568738213, "learning_rate": 3.831964887155264e-05, "loss": 0.3863, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.519434904245049, "learning_rate": 3.829688502793403e-05, "loss": 0.3807, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.48256488903695827, "learning_rate": 3.827397488291029e-05, "loss": 0.3668, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.4643554575579673, "learning_rate": 3.8250918619670343e-05, "loss": 0.3672, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.4625276034993097, "learning_rate": 3.822771642257145e-05, "loss": 0.3456, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.505400671434797, "learning_rate": 3.820436847713776e-05, "loss": 0.3698, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.4677145102532091, "learning_rate": 3.8180874970058826e-05, "loss": 0.3679, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5026043786132084, "learning_rate": 3.8157236089188103e-05, "loss": 0.3743, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.4529509737502621, "learning_rate": 3.813345202354145e-05, "loss": 0.399, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.4711525427280295, "learning_rate": 3.810952296329563e-05, "loss": 0.3741, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.4835871881861551, "learning_rate": 3.808544909978676e-05, "loss": 0.3858, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.48842589662314767, "learning_rate": 3.806123062550882e-05, "loss": 0.3549, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.5140427512585832, "learning_rate": 3.803686773411208e-05, "loss": 0.3568, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.4395505841929517, "learning_rate": 3.801236062040158e-05, "loss": 0.365, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5769451701164086, "learning_rate": 3.798770948033553e-05, "loss": 0.3749, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4652046391295313, "learning_rate": 3.796291451102381e-05, "loss": 0.3783, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5377378928203618, "learning_rate": 3.793797591072631e-05, "loss": 0.3598, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.542124871841715, "learning_rate": 3.791289387885144e-05, "loss": 0.3879, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4992568317831407, "learning_rate": 3.788766861595443e-05, "loss": 0.3621, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5197974278925541, "learning_rate": 3.7862300323735835e-05, "loss": 0.3655, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5212849490905996, "learning_rate": 3.783678920503983e-05, "loss": 0.3748, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.47685874969715475, "learning_rate": 3.781113546385265e-05, "loss": 0.3551, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.5057097227724436, "learning_rate": 3.7785339305300916e-05, "loss": 0.3792, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.4238576127819523, "learning_rate": 3.7759400935650025e-05, "loss": 0.3644, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.49644590681210277, "learning_rate": 3.77333205623025e-05, "loss": 0.3365, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.4749935137357689, "learning_rate": 3.7707098393796295e-05, "loss": 0.3666, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.45340954761571356, "learning_rate": 3.7680734639803185e-05, "loss": 0.3811, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.4569941481313673, "learning_rate": 3.765422951112704e-05, "loss": 0.3719, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.3830673911549311, "learning_rate": 3.762758321970216e-05, "loss": 0.3616, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.43741855316375094, "learning_rate": 3.7600795978591584e-05, "loss": 0.3593, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.4245687200668723, "learning_rate": 3.757386800198538e-05, "loss": 0.359, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.4355217827976667, "learning_rate": 3.7546799505198925e-05, "loss": 0.3465, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.42246868089011635, "learning_rate": 3.7519590704671197e-05, "loss": 0.36, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4620291688718257, "learning_rate": 3.749224181796305e-05, "loss": 0.3856, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.44165060592589833, "learning_rate": 3.746475306375545e-05, "loss": 0.3434, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.4545282945007612, "learning_rate": 3.743712466184774e-05, "loss": 0.3907, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.4429442897522955, "learning_rate": 3.7409356833155885e-05, "loss": 0.3705, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4351497674563988, "learning_rate": 3.73814497997107e-05, "loss": 0.3603, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.4411156221209338, "learning_rate": 3.7353403784656095e-05, "loss": 0.3848, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.4549486593085145, "learning_rate": 3.732521901224724e-05, "loss": 0.3685, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.47382392436533577, "learning_rate": 3.7296895707848844e-05, "loss": 0.3646, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.5010418660069251, "learning_rate": 3.7268434097933275e-05, "loss": 0.3775, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.4925664910053554, "learning_rate": 3.723983441007882e-05, "loss": 0.3688, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5294817427380312, "learning_rate": 3.721109687296781e-05, "loss": 0.3612, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.4659978707846597, "learning_rate": 3.718222171638484e-05, "loss": 0.3773, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5210961147760816, "learning_rate": 3.715320917121488e-05, "loss": 0.372, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.40928054749890275, "learning_rate": 3.712405946944149e-05, "loss": 0.3672, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.497039464019632, "learning_rate": 3.709477284414488e-05, "loss": 0.3553, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.408849530069066, "learning_rate": 3.7065349529500136e-05, "loss": 0.3687, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.5446200449013873, "learning_rate": 3.7035789760775305e-05, "loss": 0.3697, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.43448760671655134, "learning_rate": 3.70060937743295e-05, "loss": 0.3476, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.48344898431101785, "learning_rate": 3.6976261807611045e-05, "loss": 0.3581, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.47137516909714455, "learning_rate": 3.694629409915555e-05, "loss": 0.3723, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4666023063261915, "learning_rate": 3.691619088858401e-05, "loss": 0.3644, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.460267501951164, "learning_rate": 3.68859524166009e-05, "loss": 0.3631, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.496839456387307, "learning_rate": 3.6855578924992226e-05, "loss": 0.4088, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.5254012074138844, "learning_rate": 3.6825070656623626e-05, "loss": 0.3514, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.4392560106301562, "learning_rate": 3.67944278554384e-05, "loss": 0.3839, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.5456209911932174, "learning_rate": 3.676365076645557e-05, "loss": 0.384, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4639262955504118, "learning_rate": 3.673273963576791e-05, "loss": 0.348, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.5707303339508044, "learning_rate": 3.670169471054001e-05, "loss": 0.3485, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.45024932694892245, "learning_rate": 3.6670516239006254e-05, "loss": 0.3663, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4778995782122157, "learning_rate": 3.663920447046888e-05, "loss": 0.3591, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.4096053909722946, "learning_rate": 3.6607759655295954e-05, "loss": 0.3756, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.46432684529056484, "learning_rate": 3.657618204491937e-05, "loss": 0.3714, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.43846981491123654, "learning_rate": 3.6544471891832875e-05, "loss": 0.3699, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.44574831444896995, "learning_rate": 3.6512629449589983e-05, "loss": 0.3615, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.41162510615281683, "learning_rate": 3.6480654972802045e-05, "loss": 0.355, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.4462119390519313, "learning_rate": 3.644854871713611e-05, "loss": 0.3506, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.4307166327461711, "learning_rate": 3.6416310939312924e-05, "loss": 0.3565, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.40806848613732566, "learning_rate": 3.638394189710493e-05, "loss": 0.341, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.4412225818445255, "learning_rate": 3.635144184933412e-05, "loss": 0.3796, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.4378641910848102, "learning_rate": 3.6318811055869994e-05, "loss": 0.3606, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.4389062559714023, "learning_rate": 3.628604977762752e-05, "loss": 0.3588, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.4087806620737165, "learning_rate": 3.6253158276565004e-05, "loss": 0.352, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.4521674937417754, "learning_rate": 3.6220136815682016e-05, "loss": 0.3856, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.5104171889657383, "learning_rate": 3.618698565901727e-05, "loss": 0.3727, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.41598301601772714, "learning_rate": 3.615370507164654e-05, "loss": 0.367, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.4237776690918798, "learning_rate": 3.61202953196805e-05, "loss": 0.411, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.38786024694546956, "learning_rate": 3.6086756670262654e-05, "loss": 0.3615, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.41037537415602743, "learning_rate": 3.6053089391567135e-05, "loss": 0.3895, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.422977888156506, "learning_rate": 3.601929375279662e-05, "loss": 0.3567, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.4080913709537222, "learning_rate": 3.598537002418012e-05, "loss": 0.3877, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.46197886065942684, "learning_rate": 3.5951318476970885e-05, "loss": 0.372, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.4325400256911984, "learning_rate": 3.591713938344416e-05, "loss": 0.3732, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.5133566838779298, "learning_rate": 3.588283301689507e-05, "loss": 0.3717, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.4303786073102725, "learning_rate": 3.5848399651636424e-05, "loss": 0.3851, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.5005828285768976, "learning_rate": 3.5813839562996473e-05, "loss": 0.3855, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.4306545608728379, "learning_rate": 3.5779153027316775e-05, "loss": 0.363, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.425545690947071, "learning_rate": 3.574434032194994e-05, "loss": 0.3702, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.44161789497019655, "learning_rate": 3.5709401725257436e-05, "loss": 0.387, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4404250199416638, "learning_rate": 3.5674337516607346e-05, "loss": 0.3508, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.404603953890511, "learning_rate": 3.563914797637216e-05, "loss": 0.3297, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.46825294800697426, "learning_rate": 3.560383338592649e-05, "loss": 0.3817, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.4074812261202699, "learning_rate": 3.556839402764487e-05, "loss": 0.3858, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.42900030590881505, "learning_rate": 3.553283018489946e-05, "loss": 0.376, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.45777855677567, "learning_rate": 3.54971421420578e-05, "loss": 0.3638, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.39294978677899206, "learning_rate": 3.5461330184480524e-05, "loss": 0.3579, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4361184343671776, "learning_rate": 3.54253945985191e-05, "loss": 0.3607, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4251241994472822, "learning_rate": 3.5389335671513524e-05, "loss": 0.3815, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.39844835456803035, "learning_rate": 3.5353153691789986e-05, "loss": 0.3596, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.41058636144199895, "learning_rate": 3.531684894865866e-05, "loss": 0.3623, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4506579569228027, "learning_rate": 3.528042173241128e-05, "loss": 0.364, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.40446084024114826, "learning_rate": 3.524387233431892e-05, "loss": 0.3679, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.49388164976128357, "learning_rate": 3.520720104662958e-05, "loss": 0.3693, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.39380757733003724, "learning_rate": 3.5170408162565904e-05, "loss": 0.3587, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.449892385077521, "learning_rate": 3.513349397632281e-05, "loss": 0.3589, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.43936557837793433, "learning_rate": 3.5096458783065145e-05, "loss": 0.3622, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.35447789560593845, "learning_rate": 3.505930287892533e-05, "loss": 0.3658, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.493055075462385, "learning_rate": 3.502202656100099e-05, "loss": 0.39, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.3766359985220278, "learning_rate": 3.498463012735256e-05, "loss": 0.3468, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.453761413112153, "learning_rate": 3.494711387700094e-05, "loss": 0.3645, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.42259325280863785, "learning_rate": 3.490947810992505e-05, "loss": 0.3562, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.4691507361883626, "learning_rate": 3.48717231270595e-05, "loss": 0.3541, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4527100821289943, "learning_rate": 3.483384923029211e-05, "loss": 0.3721, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.4465074191826469, "learning_rate": 3.479585672246156e-05, "loss": 0.3785, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.4757062359903578, "learning_rate": 3.4757745907354924e-05, "loss": 0.3804, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.41151603651058427, "learning_rate": 3.471951708970527e-05, "loss": 0.3802, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.49108110339871813, "learning_rate": 3.468117057518921e-05, "loss": 0.3853, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.40058066798812, "learning_rate": 3.4642706670424426e-05, "loss": 0.3766, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.44514335788252185, "learning_rate": 3.460412568296731e-05, "loss": 0.3463, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.4969324071247305, "learning_rate": 3.456542792131039e-05, "loss": 0.3582, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.4345453380412306, "learning_rate": 3.4526613694879936e-05, "loss": 0.3751, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.4868979157536691, "learning_rate": 3.448768331403348e-05, "loss": 0.3775, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.38286316287395616, "learning_rate": 3.44486370900573e-05, "loss": 0.3617, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.4750485259412508, "learning_rate": 3.440947533516396e-05, "loss": 0.3435, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.39939386978215224, "learning_rate": 3.4370198362489816e-05, "loss": 0.3602, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.4483898062143403, "learning_rate": 3.43308064860925e-05, "loss": 0.3752, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.4758777212455939, "learning_rate": 3.4291300020948393e-05, "loss": 0.3501, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.4666275607879542, "learning_rate": 3.425167928295015e-05, "loss": 0.3545, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.41441984321491565, "learning_rate": 3.421194458890411e-05, "loss": 0.3668, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.417919609634946, "learning_rate": 3.4172096256527865e-05, "loss": 0.373, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.43593375892332553, "learning_rate": 3.4132134604447595e-05, "loss": 0.3732, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.4333373751930691, "learning_rate": 3.409205995219561e-05, "loss": 0.4004, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.44060974936612557, "learning_rate": 3.4051872620207765e-05, "loss": 0.3599, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.40489117001072106, "learning_rate": 3.40115729298209e-05, "loss": 0.3753, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.41294499458771605, "learning_rate": 3.397116120327025e-05, "loss": 0.3649, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.49385875364544773, "learning_rate": 3.3930637763686916e-05, "loss": 0.3754, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.41943093948988197, "learning_rate": 3.389000293509524e-05, "loss": 0.367, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.4898053072771614, "learning_rate": 3.3849257042410225e-05, "loss": 0.3841, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.44830076046717876, "learning_rate": 3.380840041143494e-05, "loss": 0.3828, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.47912141361796234, "learning_rate": 3.376743336885792e-05, "loss": 0.3715, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4120316323861365, "learning_rate": 3.372635624225055e-05, "loss": 0.3749, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.4659661406630498, "learning_rate": 3.3685169360064445e-05, "loss": 0.3574, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4862179683825515, "learning_rate": 3.3643873051628804e-05, "loss": 0.3762, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.39501864636497586, "learning_rate": 3.3602467647147814e-05, "loss": 0.3767, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.448374155138281, "learning_rate": 3.356095347769799e-05, "loss": 0.332, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.42444884283387324, "learning_rate": 3.351933087522552e-05, "loss": 0.3835, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.4097627426224432, "learning_rate": 3.3477600172543626e-05, "loss": 0.3627, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.4138757828153558, "learning_rate": 3.3435761703329894e-05, "loss": 0.3899, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.47909608046343993, "learning_rate": 3.3393815802123606e-05, "loss": 0.3678, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.41169215354064365, "learning_rate": 3.335176280432308e-05, "loss": 0.3595, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.47422319205952795, "learning_rate": 3.330960304618295e-05, "loss": 0.3851, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4031281692210969, "learning_rate": 3.326733686481153e-05, "loss": 0.3718, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.43529840857827107, "learning_rate": 3.3224964598168084e-05, "loss": 0.357, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.3759823454497756, "learning_rate": 3.318248658506012e-05, "loss": 0.3576, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.40266504434998046, "learning_rate": 3.313990316514069e-05, "loss": 0.3723, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.4117189436567322, "learning_rate": 3.309721467890571e-05, "loss": 0.3646, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.4337553808706112, "learning_rate": 3.305442146769115e-05, "loss": 0.3718, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.4256551319533573, "learning_rate": 3.30115238736704e-05, "loss": 0.3781, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.4344042889287349, "learning_rate": 3.296852223985148e-05, "loss": 0.3381, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3786081615028819, "learning_rate": 3.2925416910074315e-05, "loss": 0.3607, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.4002412919783543, "learning_rate": 3.288220822900796e-05, "loss": 0.3488, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.44339155603255426, "learning_rate": 3.283889654214788e-05, "loss": 0.3624, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.4177994680908189, "learning_rate": 3.279548219581317e-05, "loss": 0.3727, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.3971613410441534, "learning_rate": 3.275196553714379e-05, "loss": 0.3637, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.439925543847691, "learning_rate": 3.270834691409778e-05, "loss": 0.3794, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.4299948905307882, "learning_rate": 3.266462667544849e-05, "loss": 0.3872, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.449972272176414, "learning_rate": 3.262080517078178e-05, "loss": 0.3546, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.42070294725431556, "learning_rate": 3.257688275049323e-05, "loss": 0.3927, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.3819259830982237, "learning_rate": 3.253285976578535e-05, "loss": 0.3665, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.4072712130412378, "learning_rate": 3.2488736568664756e-05, "loss": 0.3792, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.40467796440946935, "learning_rate": 3.244451351193935e-05, "loss": 0.3804, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.38335366890528394, "learning_rate": 3.240019094921551e-05, "loss": 0.3624, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.4078702961140357, "learning_rate": 3.235576923489527e-05, "loss": 0.3528, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.3793016376946511, "learning_rate": 3.2311248724173476e-05, "loss": 0.3595, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.4075347683883136, "learning_rate": 3.226662977303494e-05, "loss": 0.373, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4716963295654284, "learning_rate": 3.2221912738251626e-05, "loss": 0.3868, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.4215211891847023, "learning_rate": 3.2177097977379736e-05, "loss": 0.3598, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.4209339079995427, "learning_rate": 3.21321858487569e-05, "loss": 0.3729, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.392565271597808, "learning_rate": 3.208717671149931e-05, "loss": 0.3543, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.43724247741381145, "learning_rate": 3.204207092549882e-05, "loss": 0.3631, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.47268233654978803, "learning_rate": 3.19968688514201e-05, "loss": 0.3705, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.534984794917675, "learning_rate": 3.195157085069774e-05, "loss": 0.3779, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.4774081909149461, "learning_rate": 3.190617728553332e-05, "loss": 0.3827, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.46882691647022584, "learning_rate": 3.1860688518892606e-05, "loss": 0.3627, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.41037111148808336, "learning_rate": 3.181510491450254e-05, "loss": 0.3963, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.47108400431805053, "learning_rate": 3.176942683684842e-05, "loss": 0.3689, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.42128297274179705, "learning_rate": 3.1723654651170934e-05, "loss": 0.3531, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.41696150857443576, "learning_rate": 3.167778872346327e-05, "loss": 0.3655, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.38557434168315124, "learning_rate": 3.163182942046815e-05, "loss": 0.3708, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.41173652383347875, "learning_rate": 3.158577710967494e-05, "loss": 0.3505, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.4152964100799042, "learning_rate": 3.153963215931669e-05, "loss": 0.371, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.3882035298947647, "learning_rate": 3.14933949383672e-05, "loss": 0.3676, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.3891036077721201, "learning_rate": 3.144706581653805e-05, "loss": 0.3632, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.4016540669266484, "learning_rate": 3.140064516427566e-05, "loss": 0.3547, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.39011898690580754, "learning_rate": 3.135413335275833e-05, "loss": 0.3622, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.43495004277050187, "learning_rate": 3.130753075389327e-05, "loss": 0.3696, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4063195206939467, "learning_rate": 3.1260837740313625e-05, "loss": 0.3624, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.48132697899830107, "learning_rate": 3.121405468537547e-05, "loss": 0.3567, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.4425073378080081, "learning_rate": 3.116718196315488e-05, "loss": 0.3524, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.3596073544566815, "learning_rate": 3.1120219948444894e-05, "loss": 0.3516, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.42540287587706593, "learning_rate": 3.107316901675252e-05, "loss": 0.3761, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3939865332456466, "learning_rate": 3.1026029544295745e-05, "loss": 0.3697, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.41727444981610073, "learning_rate": 3.097880190800057e-05, "loss": 0.3935, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.39860672039344786, "learning_rate": 3.093148648549788e-05, "loss": 0.3325, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.43006108292853007, "learning_rate": 3.088408365512055e-05, "loss": 0.371, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.4539839878663164, "learning_rate": 3.083659379590034e-05, "loss": 0.3869, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.4231971524165308, "learning_rate": 3.0789017287564913e-05, "loss": 0.3756, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.5094827704523884, "learning_rate": 3.074135451053475e-05, "loss": 0.381, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.4460044634410282, "learning_rate": 3.069360584592015e-05, "loss": 0.3819, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.5038994890299141, "learning_rate": 3.064577167551816e-05, "loss": 0.3828, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.3894232230746623, "learning_rate": 3.059785238180953e-05, "loss": 0.3905, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.5357710970056775, "learning_rate": 3.054984834795566e-05, "loss": 0.4018, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.41666127312730383, "learning_rate": 3.0501759957795537e-05, "loss": 0.3777, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.5024812158229848, "learning_rate": 3.0453587595842627e-05, "loss": 0.3705, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4393159209167542, "learning_rate": 3.0405331647281856e-05, "loss": 0.3556, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.4112773342634208, "learning_rate": 3.0356992497966508e-05, "loss": 0.3423, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.40714021839019876, "learning_rate": 3.0308570534415137e-05, "loss": 0.356, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.40715902166103457, "learning_rate": 3.0260066143808467e-05, "loss": 0.3733, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.3921894197715338, "learning_rate": 3.021147971398632e-05, "loss": 0.3823, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.3817648459206123, "learning_rate": 3.0162811633444478e-05, "loss": 0.3649, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.3781308448721005, "learning_rate": 3.0114062291331635e-05, "loss": 0.3832, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.39631104757447544, "learning_rate": 3.0065232077446217e-05, "loss": 0.3604, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.3964089368711006, "learning_rate": 3.001632138223332e-05, "loss": 0.3674, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.5858885104830336, "learning_rate": 2.9967330596781565e-05, "loss": 0.2772, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.38195866853500005, "learning_rate": 2.9918260112819952e-05, "loss": 0.2718, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.8662025906637915, "learning_rate": 2.9869110322714778e-05, "loss": 0.2644, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.47382442538873926, "learning_rate": 2.9819881619466447e-05, "loss": 0.2401, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.4754607300829452, "learning_rate": 2.9770574396706364e-05, "loss": 0.2884, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.497593530549183, "learning_rate": 2.972118904869376e-05, "loss": 0.2589, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4326867060946374, "learning_rate": 2.9671725970312563e-05, "loss": 0.2678, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.4087753677728313, "learning_rate": 2.9622185557068238e-05, "loss": 0.245, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.49769299466751504, "learning_rate": 2.95725682050846e-05, "loss": 0.2486, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.447288846060043, "learning_rate": 2.9522874311100684e-05, "loss": 0.2547, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.4782627708559365, "learning_rate": 2.9473104272467526e-05, "loss": 0.2391, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.42965859714637394, "learning_rate": 2.942325848714505e-05, "loss": 0.2283, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.47806000199614485, "learning_rate": 2.9373337353698804e-05, "loss": 0.2537, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4115133743840998, "learning_rate": 2.932334127129686e-05, "loss": 0.2565, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.43381623498631106, "learning_rate": 2.9273270639706547e-05, "loss": 0.2455, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.40507696979158325, "learning_rate": 2.922312585929131e-05, "loss": 0.2702, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.42507069661110225, "learning_rate": 2.9172907331007478e-05, "loss": 0.2516, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.39462643746143006, "learning_rate": 2.9122615456401053e-05, "loss": 0.2421, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.42943367501930463, "learning_rate": 2.9072250637604535e-05, "loss": 0.248, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3557951853185583, "learning_rate": 2.9021813277333667e-05, "loss": 0.2193, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.39732204480573147, "learning_rate": 2.8971303778884244e-05, "loss": 0.2457, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3448604380111077, "learning_rate": 2.8920722546128863e-05, "loss": 0.261, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.3870026929270955, "learning_rate": 2.887006998351372e-05, "loss": 0.2744, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.377643549045063, "learning_rate": 2.881934649605535e-05, "loss": 0.2467, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.40888988960099476, "learning_rate": 2.8768552489337408e-05, "loss": 0.2699, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.38210484765320935, "learning_rate": 2.8717688369507425e-05, "loss": 0.2601, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.3651850166152361, "learning_rate": 2.8666754543273535e-05, "loss": 0.2513, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.40532815222134716, "learning_rate": 2.8615751417901273e-05, "loss": 0.2424, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3729683765795903, "learning_rate": 2.856467940121025e-05, "loss": 0.2646, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.4145756644393828, "learning_rate": 2.8513538901570964e-05, "loss": 0.2477, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3495526553419234, "learning_rate": 2.846233032790149e-05, "loss": 0.2327, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.403557984494112, "learning_rate": 2.84110540896642e-05, "loss": 0.2478, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.4021246081664659, "learning_rate": 2.8359710596862555e-05, "loss": 0.2367, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.3889358634495636, "learning_rate": 2.8308300260037734e-05, "loss": 0.2305, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.39704017221795257, "learning_rate": 2.8256823490265424e-05, "loss": 0.237, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.398466844501125, "learning_rate": 2.8205280699152515e-05, "loss": 0.2454, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.4413454852111532, "learning_rate": 2.8153672298833777e-05, "loss": 0.2479, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.40410095143104, "learning_rate": 2.8101998701968615e-05, "loss": 0.2525, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.38707031593857183, "learning_rate": 2.805026032173773e-05, "loss": 0.2552, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.4241065647351759, "learning_rate": 2.7998457571839832e-05, "loss": 0.2624, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.43559013818633857, "learning_rate": 2.7946590866488322e-05, "loss": 0.2687, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.3855877427239653, "learning_rate": 2.7894660620408e-05, "loss": 0.2524, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.40401005822603403, "learning_rate": 2.784266724883173e-05, "loss": 0.273, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3890081185398496, "learning_rate": 2.7790611167497128e-05, "loss": 0.2475, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3662791717293835, "learning_rate": 2.7738492792643224e-05, "loss": 0.2568, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3694110491477064, "learning_rate": 2.768631254100716e-05, "loss": 0.251, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.39330838188552325, "learning_rate": 2.7634070829820836e-05, "loss": 0.251, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.4185661622566164, "learning_rate": 2.7581768076807592e-05, "loss": 0.2468, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.35308191736207756, "learning_rate": 2.7529404700178832e-05, "loss": 0.2476, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3975341750201081, "learning_rate": 2.7476981118630735e-05, "loss": 0.2412, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.36304198867869575, "learning_rate": 2.742449775134085e-05, "loss": 0.2619, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.3839388730735694, "learning_rate": 2.7371955017964788e-05, "loss": 0.2425, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.38309019539656647, "learning_rate": 2.7319353338632845e-05, "loss": 0.2541, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.40344885284567883, "learning_rate": 2.7266693133946645e-05, "loss": 0.2404, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.3730547038106111, "learning_rate": 2.7213974824975785e-05, "loss": 0.2576, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3784488401184954, "learning_rate": 2.7161198833254464e-05, "loss": 0.2524, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.36164720027402275, "learning_rate": 2.7108365580778095e-05, "loss": 0.2328, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.38419524969776925, "learning_rate": 2.705547548999996e-05, "loss": 0.2558, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.3711561391156748, "learning_rate": 2.7002528983827817e-05, "loss": 0.2547, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.395079204528693, "learning_rate": 2.6949526485620517e-05, "loss": 0.2543, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.38208487823687365, "learning_rate": 2.6896468419184623e-05, "loss": 0.2677, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.4295747859695341, "learning_rate": 2.6843355208771024e-05, "loss": 0.2716, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.4013564608488305, "learning_rate": 2.6790187279071536e-05, "loss": 0.253, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.40661715504065854, "learning_rate": 2.67369650552155e-05, "loss": 0.2674, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.39983503782562896, "learning_rate": 2.6683688962766407e-05, "loss": 0.2472, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.4179840494165635, "learning_rate": 2.6630359427718468e-05, "loss": 0.266, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.42921615726210843, "learning_rate": 2.6576976876493225e-05, "loss": 0.2549, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.4468857364370614, "learning_rate": 2.652354173593614e-05, "loss": 0.2413, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.39615768171785365, "learning_rate": 2.647005443331317e-05, "loss": 0.2586, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.40464259028180244, "learning_rate": 2.6416515396307354e-05, "loss": 0.2415, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3767087926652098, "learning_rate": 2.636292505301542e-05, "loss": 0.2583, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.40152575838218263, "learning_rate": 2.630928383194431e-05, "loss": 0.2458, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3834608401199028, "learning_rate": 2.625559216200781e-05, "loss": 0.247, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.38811367863524565, "learning_rate": 2.620185047252308e-05, "loss": 0.2541, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.38017828304175394, "learning_rate": 2.614805919320723e-05, "loss": 0.2595, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3494804518054667, "learning_rate": 2.6094218754173895e-05, "loss": 0.2606, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.4060831449112486, "learning_rate": 2.60403295859298e-05, "loss": 0.2539, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.4033557375521465, "learning_rate": 2.5986392119371297e-05, "loss": 0.2744, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.3917793414148777, "learning_rate": 2.5932406785780928e-05, "loss": 0.2598, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.41365477936553063, "learning_rate": 2.5878374016823987e-05, "loss": 0.2641, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.3629301110889228, "learning_rate": 2.5824294244545045e-05, "loss": 0.2566, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.4074577060813001, "learning_rate": 2.577016790136453e-05, "loss": 0.2617, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3721885872386473, "learning_rate": 2.5715995420075225e-05, "loss": 0.2438, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.3729466955233492, "learning_rate": 2.5661777233838864e-05, "loss": 0.2682, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3942818190341062, "learning_rate": 2.5607513776182616e-05, "loss": 0.2642, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.37427573889032745, "learning_rate": 2.5553205480995633e-05, "loss": 0.2833, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.37394729529497184, "learning_rate": 2.5498852782525604e-05, "loss": 0.264, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.39895986268057704, "learning_rate": 2.5444456115375252e-05, "loss": 0.264, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3884372094675381, "learning_rate": 2.539001591449889e-05, "loss": 0.2391, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.3655775467996362, "learning_rate": 2.53355326151989e-05, "loss": 0.2537, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3935058304312032, "learning_rate": 2.5281006653122288e-05, "loss": 0.235, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3622602856957144, "learning_rate": 2.5226438464257217e-05, "loss": 0.2405, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3844106683293587, "learning_rate": 2.5171828484929447e-05, "loss": 0.2851, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.34357792893890754, "learning_rate": 2.5117177151798934e-05, "loss": 0.2605, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.38932011351594925, "learning_rate": 2.506248490185627e-05, "loss": 0.2466, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.38765424876202387, "learning_rate": 2.500775217241923e-05, "loss": 0.2465, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3897109578721407, "learning_rate": 2.4952979401129266e-05, "loss": 0.2484, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3668634551839642, "learning_rate": 2.4898167025948e-05, "loss": 0.2833, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.3801290823211938, "learning_rate": 2.4843315485153703e-05, "loss": 0.2361, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.3827004945724282, "learning_rate": 2.4788425217337856e-05, "loss": 0.26, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.3577903381045083, "learning_rate": 2.4733496661401572e-05, "loss": 0.2331, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.3946027202569565, "learning_rate": 2.4678530256552114e-05, "loss": 0.2635, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.3441932009420027, "learning_rate": 2.46235264422994e-05, "loss": 0.2667, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.3539305539335304, "learning_rate": 2.4568485658452452e-05, "loss": 0.265, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.37120109223130826, "learning_rate": 2.451340834511592e-05, "loss": 0.2837, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.36634004083426347, "learning_rate": 2.4458294942686528e-05, "loss": 0.2616, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.35005858758234965, "learning_rate": 2.440314589184958e-05, "loss": 0.266, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.3474701458307628, "learning_rate": 2.434796163357541e-05, "loss": 0.2564, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.35183811601549897, "learning_rate": 2.429274260911588e-05, "loss": 0.2525, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.3381754771121531, "learning_rate": 2.423748926000084e-05, "loss": 0.2523, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3681921206994096, "learning_rate": 2.418220202803459e-05, "loss": 0.2572, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.37909434060795155, "learning_rate": 2.412688135529237e-05, "loss": 0.2579, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3478373807732038, "learning_rate": 2.4071527684116807e-05, "loss": 0.2787, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.38412266763989816, "learning_rate": 2.4016141457114372e-05, "loss": 0.2755, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.366686075793029, "learning_rate": 2.396072311715187e-05, "loss": 0.2542, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3313722187742704, "learning_rate": 2.3905273107352863e-05, "loss": 0.2485, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.3762937516665798, "learning_rate": 2.3849791871094157e-05, "loss": 0.2397, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.33540747817789635, "learning_rate": 2.379427985200223e-05, "loss": 0.2577, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.34362394501393384, "learning_rate": 2.373873749394972e-05, "loss": 0.2568, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.38530953493395104, "learning_rate": 2.3683165241051836e-05, "loss": 0.2518, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.34729063867595594, "learning_rate": 2.3627563537662823e-05, "loss": 0.2545, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.36002548957248515, "learning_rate": 2.3571932828372433e-05, "loss": 0.2713, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3565620606066766, "learning_rate": 2.351627355800233e-05, "loss": 0.2587, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.35962439888055997, "learning_rate": 2.346058617160256e-05, "loss": 0.2645, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.36783450621343494, "learning_rate": 2.3404871114447976e-05, "loss": 0.2696, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.34145530804873925, "learning_rate": 2.334912883203469e-05, "loss": 0.2352, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.37080110288912244, "learning_rate": 2.3293359770076505e-05, "loss": 0.252, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.34976336916974216, "learning_rate": 2.323756437450136e-05, "loss": 0.2373, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.44247045172770927, "learning_rate": 2.3181743091447754e-05, "loss": 0.2432, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.3610002292124315, "learning_rate": 2.3125896367261164e-05, "loss": 0.2596, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.34327147357359405, "learning_rate": 2.307002464849052e-05, "loss": 0.2626, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.34964361983872805, "learning_rate": 2.30141283818846e-05, "loss": 0.2555, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3732995831403715, "learning_rate": 2.2958208014388462e-05, "loss": 0.2431, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3566494188347554, "learning_rate": 2.2902263993139857e-05, "loss": 0.2408, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.36930193633770114, "learning_rate": 2.2846296765465708e-05, "loss": 0.255, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3581855728530781, "learning_rate": 2.2790306778878465e-05, "loss": 0.2601, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.3551177559478229, "learning_rate": 2.273429448107257e-05, "loss": 0.2452, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3868535705191991, "learning_rate": 2.2678260319920868e-05, "loss": 0.2557, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.33726945601347025, "learning_rate": 2.262220474347102e-05, "loss": 0.2566, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.35957909960189965, "learning_rate": 2.2566128199941918e-05, "loss": 0.2508, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.3675870897372701, "learning_rate": 2.2510031137720104e-05, "loss": 0.2567, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.373579644196931, "learning_rate": 2.2453914005356206e-05, "loss": 0.263, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.3555717004614328, "learning_rate": 2.2397777251561302e-05, "loss": 0.2688, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3811797500565481, "learning_rate": 2.2341621325203393e-05, "loss": 0.2692, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.34626039186706953, "learning_rate": 2.2285446675303764e-05, "loss": 0.2721, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.3683619590330008, "learning_rate": 2.2229253751033423e-05, "loss": 0.2514, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.35672562008110864, "learning_rate": 2.2173043001709492e-05, "loss": 0.277, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.362980166968024, "learning_rate": 2.2116814876791627e-05, "loss": 0.2704, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.37750486122083005, "learning_rate": 2.2060569825878413e-05, "loss": 0.2492, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.3431284832444233, "learning_rate": 2.2004308298703777e-05, "loss": 0.2521, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3771369432380341, "learning_rate": 2.1948030745133396e-05, "loss": 0.2743, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3628157014392677, "learning_rate": 2.1891737615161083e-05, "loss": 0.2661, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3542748254375687, "learning_rate": 2.1835429358905218e-05, "loss": 0.2631, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.40363511116456435, "learning_rate": 2.17791064266051e-05, "loss": 0.2602, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.3752144645816542, "learning_rate": 2.172276926861741e-05, "loss": 0.2236, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.41448322390295933, "learning_rate": 2.166641833541255e-05, "loss": 0.2533, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.36317726300960324, "learning_rate": 2.161005407757109e-05, "loss": 0.2411, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3780232639684, "learning_rate": 2.155367694578013e-05, "loss": 0.2825, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.41841710872346444, "learning_rate": 2.1497287390829712e-05, "loss": 0.2777, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.3718259600555056, "learning_rate": 2.1440885863609208e-05, "loss": 0.247, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.3922095177552867, "learning_rate": 2.1384472815103737e-05, "loss": 0.255, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.40098799338974744, "learning_rate": 2.1328048696390534e-05, "loss": 0.2489, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.37132492789733307, "learning_rate": 2.1271613958635342e-05, "loss": 0.2377, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.5129318327227613, "learning_rate": 2.1215169053088825e-05, "loss": 0.2613, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.443150685390177, "learning_rate": 2.1158714431082937e-05, "loss": 0.2453, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3788812122726128, "learning_rate": 2.110225054402733e-05, "loss": 0.2414, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.36586828457554815, "learning_rate": 2.1045777843405747e-05, "loss": 0.2445, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.3573617180860621, "learning_rate": 2.09892967807724e-05, "loss": 0.2423, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3777880000939294, "learning_rate": 2.093280780774835e-05, "loss": 0.2671, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.35272380281061066, "learning_rate": 2.087631137601793e-05, "loss": 0.2489, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.34294257659078076, "learning_rate": 2.0819807937325104e-05, "loss": 0.2557, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.3371959885968004, "learning_rate": 2.0763297943469847e-05, "loss": 0.2533, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.34161895613920706, "learning_rate": 2.070678184630458e-05, "loss": 0.2729, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.34196494848709896, "learning_rate": 2.06502600977305e-05, "loss": 0.2634, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3394630800702062, "learning_rate": 2.0593733149694008e-05, "loss": 0.2432, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.357541196733306, "learning_rate": 2.0537201454183074e-05, "loss": 0.2476, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3712991847816984, "learning_rate": 2.0480665463223626e-05, "loss": 0.2893, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3819468488791139, "learning_rate": 2.042412562887594e-05, "loss": 0.2442, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.35009871254349023, "learning_rate": 2.0367582403231033e-05, "loss": 0.2573, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.39516312579636276, "learning_rate": 2.0311036238407023e-05, "loss": 0.2483, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.36689197896183523, "learning_rate": 2.0254487586545534e-05, "loss": 0.2503, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3394383165588366, "learning_rate": 2.0197936899808088e-05, "loss": 0.2413, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.4011478477993066, "learning_rate": 2.0141384630372466e-05, "loss": 0.2443, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.3845317199160366, "learning_rate": 2.0084831230429106e-05, "loss": 0.2344, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.39326808197932195, "learning_rate": 2.0028277152177492e-05, "loss": 0.2337, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3700639025482952, "learning_rate": 1.9971722847822518e-05, "loss": 0.2541, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3825070634852312, "learning_rate": 1.99151687695709e-05, "loss": 0.249, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.3728880069873254, "learning_rate": 1.9858615369627537e-05, "loss": 0.2688, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.3487963909323806, "learning_rate": 1.9802063100191916e-05, "loss": 0.2688, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.4124804800128025, "learning_rate": 1.974551241345447e-05, "loss": 0.2646, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.35027902773765773, "learning_rate": 1.9688963761592984e-05, "loss": 0.2631, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3506346012547704, "learning_rate": 1.963241759676897e-05, "loss": 0.2716, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.40693446719982895, "learning_rate": 1.9575874371124066e-05, "loss": 0.2598, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.37607486490129705, "learning_rate": 1.951933453677638e-05, "loss": 0.2471, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.3677576646166237, "learning_rate": 1.9462798545816932e-05, "loss": 0.2714, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.3926797561288672, "learning_rate": 1.9406266850305996e-05, "loss": 0.278, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.33466753082490924, "learning_rate": 1.9349739902269503e-05, "loss": 0.2592, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.34608762975774227, "learning_rate": 1.9293218153695425e-05, "loss": 0.2717, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.3503958547625697, "learning_rate": 1.9236702056530153e-05, "loss": 0.2531, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.36823311726046065, "learning_rate": 1.9180192062674907e-05, "loss": 0.2558, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.359338078145313, "learning_rate": 1.9123688623982076e-05, "loss": 0.247, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3695508469600145, "learning_rate": 1.906719219225165e-05, "loss": 0.2911, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.3604130458386558, "learning_rate": 1.9010703219227603e-05, "loss": 0.2528, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.3506071860024237, "learning_rate": 1.8954222156594256e-05, "loss": 0.2484, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.3505854137923815, "learning_rate": 1.8897749455972673e-05, "loss": 0.2348, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.3503997582830625, "learning_rate": 1.884128556891707e-05, "loss": 0.2494, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.3707177270934719, "learning_rate": 1.878483094691119e-05, "loss": 0.2383, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.34665517301333565, "learning_rate": 1.8728386041364664e-05, "loss": 0.2402, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.34297420778596005, "learning_rate": 1.867195130360947e-05, "loss": 0.2603, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3455052646424187, "learning_rate": 1.8615527184896263e-05, "loss": 0.2479, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.3871977542387265, "learning_rate": 1.8559114136390795e-05, "loss": 0.2555, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.3738351271319878, "learning_rate": 1.8502712609170298e-05, "loss": 0.2557, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.38542382999527597, "learning_rate": 1.8446323054219876e-05, "loss": 0.2576, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.4062782121086833, "learning_rate": 1.838994592242891e-05, "loss": 0.2796, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.3627880113490622, "learning_rate": 1.8333581664587453e-05, "loss": 0.2395, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.38002947899650374, "learning_rate": 1.8277230731382593e-05, "loss": 0.2426, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3465277647479157, "learning_rate": 1.82208935733949e-05, "loss": 0.2448, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.4175460074366457, "learning_rate": 1.8164570641094793e-05, "loss": 0.2275, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.36324670323373554, "learning_rate": 1.810826238483892e-05, "loss": 0.249, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.3537249462506229, "learning_rate": 1.8051969254866608e-05, "loss": 0.2443, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.35351087794602776, "learning_rate": 1.7995691701296226e-05, "loss": 0.2576, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.3726455391082744, "learning_rate": 1.7939430174121593e-05, "loss": 0.2896, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.34093591921030214, "learning_rate": 1.788318512320838e-05, "loss": 0.2467, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3589141568812981, "learning_rate": 1.782695699829051e-05, "loss": 0.2491, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.34760682638068946, "learning_rate": 1.7770746248966587e-05, "loss": 0.2308, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.3684488406342249, "learning_rate": 1.7714553324696243e-05, "loss": 0.2492, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3688305315888793, "learning_rate": 1.7658378674796614e-05, "loss": 0.258, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3457085532670843, "learning_rate": 1.76022227484387e-05, "loss": 0.2431, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.3478391612407495, "learning_rate": 1.7546085994643807e-05, "loss": 0.2615, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.3441951538116407, "learning_rate": 1.7489968862279902e-05, "loss": 0.214, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3845590044697914, "learning_rate": 1.743387180005809e-05, "loss": 0.2727, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.34386000145994616, "learning_rate": 1.737779525652899e-05, "loss": 0.2776, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.35187590914062505, "learning_rate": 1.732173968007914e-05, "loss": 0.255, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.36950196346770525, "learning_rate": 1.7265705518927437e-05, "loss": 0.2671, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.389365441660037, "learning_rate": 1.7209693221121542e-05, "loss": 0.2349, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.3338953889985346, "learning_rate": 1.7153703234534302e-05, "loss": 0.2477, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.3564733790276711, "learning_rate": 1.709773600686015e-05, "loss": 0.2657, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.40284085216953763, "learning_rate": 1.7041791985611548e-05, "loss": 0.2371, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.35275148028148884, "learning_rate": 1.69858716181154e-05, "loss": 0.2453, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.3506545375258432, "learning_rate": 1.692997535150948e-05, "loss": 0.2556, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.3993428599854794, "learning_rate": 1.687410363273884e-05, "loss": 0.2487, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.38988306531797795, "learning_rate": 1.6818256908552257e-05, "loss": 0.2571, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3633589089877229, "learning_rate": 1.6762435625498646e-05, "loss": 0.2461, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.35179425855769525, "learning_rate": 1.67066402299235e-05, "loss": 0.2803, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.36761187850799015, "learning_rate": 1.6650871167965313e-05, "loss": 0.2485, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.3653584984608806, "learning_rate": 1.6595128885552028e-05, "loss": 0.2452, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.3265067741545609, "learning_rate": 1.653941382839745e-05, "loss": 0.2557, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.4944552434538577, "learning_rate": 1.6483726441997673e-05, "loss": 0.1615, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.34397143089652843, "learning_rate": 1.642806717162757e-05, "loss": 0.1752, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.39166613122632954, "learning_rate": 1.637243646233718e-05, "loss": 0.1598, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.5381589206630292, "learning_rate": 1.6316834758948174e-05, "loss": 0.1655, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.45026231118643306, "learning_rate": 1.6261262506050282e-05, "loss": 0.2061, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.3926411377931895, "learning_rate": 1.620572014799777e-05, "loss": 0.1757, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.48440131816712884, "learning_rate": 1.6150208128905857e-05, "loss": 0.1723, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.43627657642062934, "learning_rate": 1.6094726892647147e-05, "loss": 0.1868, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.32721832159086445, "learning_rate": 1.6039276882848135e-05, "loss": 0.151, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.3671371787810282, "learning_rate": 1.5983858542885635e-05, "loss": 0.1633, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.39538037889967187, "learning_rate": 1.5928472315883203e-05, "loss": 0.1633, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.385725702846707, "learning_rate": 1.5873118644707633e-05, "loss": 0.1743, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.35436221372022153, "learning_rate": 1.5817797971965413e-05, "loss": 0.1918, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.339154632932761, "learning_rate": 1.576251073999917e-05, "loss": 0.1732, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.3223128727334186, "learning_rate": 1.5707257390884126e-05, "loss": 0.1663, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.36234762744185184, "learning_rate": 1.5652038366424595e-05, "loss": 0.1754, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3678120443548959, "learning_rate": 1.5596854108150424e-05, "loss": 0.173, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3184133441256618, "learning_rate": 1.5541705057313476e-05, "loss": 0.1859, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.33003241271290046, "learning_rate": 1.5486591654884086e-05, "loss": 0.1389, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3449224950033077, "learning_rate": 1.543151434154755e-05, "loss": 0.1663, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.31164611371384565, "learning_rate": 1.5376473557700615e-05, "loss": 0.1719, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.31340123484962173, "learning_rate": 1.5321469743447893e-05, "loss": 0.1882, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.3039633590305288, "learning_rate": 1.5266503338598434e-05, "loss": 0.1499, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.29324757295541265, "learning_rate": 1.5211574782662149e-05, "loss": 0.1672, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.30250404963171507, "learning_rate": 1.5156684514846307e-05, "loss": 0.1581, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3330223235650265, "learning_rate": 1.5101832974052012e-05, "loss": 0.1751, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.2916260034749104, "learning_rate": 1.5047020598870737e-05, "loss": 0.1652, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.31982758692136953, "learning_rate": 1.4992247827580778e-05, "loss": 0.16, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.3114302849418611, "learning_rate": 1.493751509814374e-05, "loss": 0.1575, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.29343637695009, "learning_rate": 1.4882822848201073e-05, "loss": 0.1512, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.3037524286751629, "learning_rate": 1.4828171515070553e-05, "loss": 0.1777, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3041874213734413, "learning_rate": 1.4773561535742793e-05, "loss": 0.1823, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.2921882068021981, "learning_rate": 1.4718993346877715e-05, "loss": 0.1637, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.2891523916615569, "learning_rate": 1.466446738480111e-05, "loss": 0.1747, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.29857049474446085, "learning_rate": 1.460998408550112e-05, "loss": 0.1753, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.30205821961914336, "learning_rate": 1.4555543884624751e-05, "loss": 0.1767, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.302507347355178, "learning_rate": 1.4501147217474402e-05, "loss": 0.1628, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.2948472877715284, "learning_rate": 1.444679451900437e-05, "loss": 0.1686, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.31697967991187875, "learning_rate": 1.4392486223817397e-05, "loss": 0.1525, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3139555615967828, "learning_rate": 1.4338222766161143e-05, "loss": 0.169, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.29716849742014356, "learning_rate": 1.4284004579924777e-05, "loss": 0.1606, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.28973768488283635, "learning_rate": 1.4229832098635479e-05, "loss": 0.17, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.29758770689579533, "learning_rate": 1.4175705755454963e-05, "loss": 0.1378, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2927045013223034, "learning_rate": 1.412162598317602e-05, "loss": 0.167, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.28485936570768694, "learning_rate": 1.406759321421907e-05, "loss": 0.1774, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3186678356013717, "learning_rate": 1.401360788062871e-05, "loss": 0.1602, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.31611922290033423, "learning_rate": 1.3959670414070204e-05, "loss": 0.1677, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.29886851227209643, "learning_rate": 1.3905781245826108e-05, "loss": 0.1508, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.3135013694821198, "learning_rate": 1.3851940806792778e-05, "loss": 0.1637, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3031730634532456, "learning_rate": 1.379814952747693e-05, "loss": 0.1501, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.30235034560729857, "learning_rate": 1.3744407837992193e-05, "loss": 0.1529, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.28833670243150994, "learning_rate": 1.3690716168055692e-05, "loss": 0.1713, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.2940195484033135, "learning_rate": 1.363707494698459e-05, "loss": 0.1613, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.2943605188654712, "learning_rate": 1.358348460369265e-05, "loss": 0.2069, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2990844746621943, "learning_rate": 1.352994556668684e-05, "loss": 0.1494, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3188272951885893, "learning_rate": 1.3476458264063865e-05, "loss": 0.1678, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.3067151846358693, "learning_rate": 1.342302312350678e-05, "loss": 0.168, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.28160980451380685, "learning_rate": 1.3369640572281537e-05, "loss": 0.1599, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.29799590869890774, "learning_rate": 1.3316311037233596e-05, "loss": 0.1471, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2906058618691401, "learning_rate": 1.326303494478451e-05, "loss": 0.1624, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.2874266932207947, "learning_rate": 1.3209812720928472e-05, "loss": 0.1775, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.29810800961810235, "learning_rate": 1.315664479122898e-05, "loss": 0.1257, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.3088185504037431, "learning_rate": 1.3103531580815378e-05, "loss": 0.1724, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.28646028283460645, "learning_rate": 1.3050473514379488e-05, "loss": 0.1653, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.3126303106372018, "learning_rate": 1.2997471016172188e-05, "loss": 0.1822, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2953160741508569, "learning_rate": 1.2944524510000042e-05, "loss": 0.1967, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2797840127457764, "learning_rate": 1.2891634419221908e-05, "loss": 0.1951, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.3121467158405149, "learning_rate": 1.2838801166745545e-05, "loss": 0.1586, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.3136487751617261, "learning_rate": 1.2786025175024216e-05, "loss": 0.1817, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.3030412190779919, "learning_rate": 1.2733306866053357e-05, "loss": 0.1718, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.30484469944932163, "learning_rate": 1.2680646661367163e-05, "loss": 0.1896, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.3075808179009976, "learning_rate": 1.2628044982035219e-05, "loss": 0.1709, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.2893940398257314, "learning_rate": 1.2575502248659155e-05, "loss": 0.1621, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2863702361279306, "learning_rate": 1.2523018881369269e-05, "loss": 0.1716, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.29860850517171217, "learning_rate": 1.2470595299821176e-05, "loss": 0.159, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.30419637142919864, "learning_rate": 1.2418231923192416e-05, "loss": 0.1685, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.30465520939313095, "learning_rate": 1.2365929170179165e-05, "loss": 0.1593, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.29897142548348615, "learning_rate": 1.2313687458992848e-05, "loss": 0.1796, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.29538538546481286, "learning_rate": 1.2261507207356785e-05, "loss": 0.1914, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.31024985810620226, "learning_rate": 1.220938883250288e-05, "loss": 0.1615, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.29314847388620213, "learning_rate": 1.215733275116827e-05, "loss": 0.1437, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.28504089078282224, "learning_rate": 1.2105339379592005e-05, "loss": 0.1681, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.30312952280665595, "learning_rate": 1.2053409133511681e-05, "loss": 0.1667, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.29310936908005575, "learning_rate": 1.2001542428160173e-05, "loss": 0.1795, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2871888177338237, "learning_rate": 1.1949739678262278e-05, "loss": 0.1701, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.29825143980376795, "learning_rate": 1.189800129803139e-05, "loss": 0.1659, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3013007912138153, "learning_rate": 1.1846327701166228e-05, "loss": 0.1543, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.298636292356752, "learning_rate": 1.1794719300847493e-05, "loss": 0.1652, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.3042584531284727, "learning_rate": 1.1743176509734582e-05, "loss": 0.1624, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.3126051701949812, "learning_rate": 1.1691699739962275e-05, "loss": 0.1607, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.3027273489475963, "learning_rate": 1.1640289403137456e-05, "loss": 0.1737, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.2968693626815181, "learning_rate": 1.1588945910335802e-05, "loss": 0.1824, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.2959494001911911, "learning_rate": 1.1537669672098517e-05, "loss": 0.1557, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.29278054186580355, "learning_rate": 1.1486461098429036e-05, "loss": 0.1498, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.2950330836882649, "learning_rate": 1.1435320598789747e-05, "loss": 0.1664, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.2979959256555701, "learning_rate": 1.1384248582098736e-05, "loss": 0.1822, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.30093428010007756, "learning_rate": 1.1333245456726467e-05, "loss": 0.1673, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2893018936150506, "learning_rate": 1.128231163049258e-05, "loss": 0.1686, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2996001176341763, "learning_rate": 1.123144751066259e-05, "loss": 0.17, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.29809005376526704, "learning_rate": 1.1180653503944657e-05, "loss": 0.1662, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.2884910512806046, "learning_rate": 1.1129930016486287e-05, "loss": 0.1555, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2897752522632821, "learning_rate": 1.107927745387114e-05, "loss": 0.1481, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.2927488982507702, "learning_rate": 1.1028696221115766e-05, "loss": 0.1587, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.28995647674493535, "learning_rate": 1.0978186722666341e-05, "loss": 0.1758, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.2922027112081009, "learning_rate": 1.0927749362395475e-05, "loss": 0.1804, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.2850925572473325, "learning_rate": 1.0877384543598954e-05, "loss": 0.1742, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.29841752134139254, "learning_rate": 1.0827092668992529e-05, "loss": 0.1568, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2933697030504625, "learning_rate": 1.077687414070869e-05, "loss": 0.1611, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.29050594903897425, "learning_rate": 1.0726729360293451e-05, "loss": 0.1726, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.2819751051075231, "learning_rate": 1.0676658728703147e-05, "loss": 0.1755, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.2974509235648073, "learning_rate": 1.0626662646301198e-05, "loss": 0.1573, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.29200284993626413, "learning_rate": 1.0576741512854958e-05, "loss": 0.1849, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2820288228501039, "learning_rate": 1.052689572753247e-05, "loss": 0.1628, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.27940359900245265, "learning_rate": 1.0477125688899328e-05, "loss": 0.1472, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.2748572014812537, "learning_rate": 1.0427431794915406e-05, "loss": 0.1625, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2954167100465411, "learning_rate": 1.0377814442931769e-05, "loss": 0.1814, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2870659181287464, "learning_rate": 1.0328274029687439e-05, "loss": 0.1726, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2954929711678965, "learning_rate": 1.0278810951306253e-05, "loss": 0.1622, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.28827241918392815, "learning_rate": 1.0229425603293647e-05, "loss": 0.1835, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.2705706393197391, "learning_rate": 1.0180118380533558e-05, "loss": 0.189, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2827680226257399, "learning_rate": 1.0130889677285225e-05, "loss": 0.1917, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.2937994744139782, "learning_rate": 1.008173988718005e-05, "loss": 0.1649, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2835750912951456, "learning_rate": 1.0032669403218439e-05, "loss": 0.1611, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.29772432098818097, "learning_rate": 9.983678617766677e-06, "loss": 0.1543, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2836992040579039, "learning_rate": 9.934767922553788e-06, "loss": 0.154, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.35840558516855126, "learning_rate": 9.885937708668371e-06, "loss": 0.1755, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.3035736839032468, "learning_rate": 9.837188366555524e-06, "loss": 0.1684, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.28494426527766625, "learning_rate": 9.788520286013691e-06, "loss": 0.168, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2886545044867722, "learning_rate": 9.739933856191537e-06, "loss": 0.1693, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2825130329179956, "learning_rate": 9.691429465584866e-06, "loss": 0.1517, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.28766077481911395, "learning_rate": 9.643007502033492e-06, "loss": 0.1512, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.2859254339223133, "learning_rate": 9.594668352718152e-06, "loss": 0.1716, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.27997562800131587, "learning_rate": 9.546412404157383e-06, "loss": 0.1472, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.2697463949786049, "learning_rate": 9.498240042204471e-06, "loss": 0.1579, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.29426094800057206, "learning_rate": 9.450151652044339e-06, "loss": 0.1561, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2917271208441194, "learning_rate": 9.402147618190472e-06, "loss": 0.1678, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.29500590586028586, "learning_rate": 9.354228324481841e-06, "loss": 0.1802, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.3063778701628173, "learning_rate": 9.306394154079852e-06, "loss": 0.1461, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.285563297660186, "learning_rate": 9.258645489465254e-06, "loss": 0.146, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.2867596887738751, "learning_rate": 9.21098271243509e-06, "loss": 0.1764, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.27957612104015184, "learning_rate": 9.163406204099659e-06, "loss": 0.1565, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.296032620972464, "learning_rate": 9.115916344879452e-06, "loss": 0.1831, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.3004734919327399, "learning_rate": 9.068513514502126e-06, "loss": 0.1693, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.27698888313099096, "learning_rate": 9.021198091999439e-06, "loss": 0.1565, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.2917513226736307, "learning_rate": 8.973970455704251e-06, "loss": 0.1447, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.3079227104064754, "learning_rate": 8.926830983247495e-06, "loss": 0.1602, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.31148010321619446, "learning_rate": 8.879780051555116e-06, "loss": 0.1822, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2883914140025295, "learning_rate": 8.83281803684512e-06, "loss": 0.1622, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.28505171645954297, "learning_rate": 8.785945314624532e-06, "loss": 0.1528, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.28879935187324823, "learning_rate": 8.739162259686385e-06, "loss": 0.1489, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.276102251054126, "learning_rate": 8.692469246106734e-06, "loss": 0.1902, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.2826149211668007, "learning_rate": 8.645866647241677e-06, "loss": 0.1686, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.3109845029058168, "learning_rate": 8.599354835724348e-06, "loss": 0.1729, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2896863057290127, "learning_rate": 8.552934183461958e-06, "loss": 0.1679, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.28503285914498727, "learning_rate": 8.506605061632805e-06, "loss": 0.1596, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.29324784243831725, "learning_rate": 8.460367840683308e-06, "loss": 0.1641, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2981376945287138, "learning_rate": 8.414222890325065e-06, "loss": 0.1648, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.28933245356509596, "learning_rate": 8.368170579531855e-06, "loss": 0.1691, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.27931947413544633, "learning_rate": 8.322211276536733e-06, "loss": 0.1555, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.2813072706899418, "learning_rate": 8.27634534882907e-06, "loss": 0.1949, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.3031985470272569, "learning_rate": 8.230573163151585e-06, "loss": 0.152, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.27877344829590783, "learning_rate": 8.184895085497466e-06, "loss": 0.1702, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.286232030991137, "learning_rate": 8.139311481107401e-06, "loss": 0.1443, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.29765554965150426, "learning_rate": 8.093822714466686e-06, "loss": 0.1494, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2876497129870028, "learning_rate": 8.048429149302271e-06, "loss": 0.1758, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2920544934300406, "learning_rate": 8.003131148579902e-06, "loss": 0.1605, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2834510086151658, "learning_rate": 7.957929074501182e-06, "loss": 0.1937, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.2974561532055619, "learning_rate": 7.912823288500695e-06, "loss": 0.1576, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.2920307373807335, "learning_rate": 7.867814151243102e-06, "loss": 0.1578, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.28478495918820784, "learning_rate": 7.822902022620267e-06, "loss": 0.1458, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.29437977245146507, "learning_rate": 7.778087261748377e-06, "loss": 0.1885, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.287689758724633, "learning_rate": 7.733370226965056e-06, "loss": 0.179, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.27348021384961696, "learning_rate": 7.688751275826527e-06, "loss": 0.1536, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.28215209594034135, "learning_rate": 7.644230765104735e-06, "loss": 0.1854, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.28537201570401743, "learning_rate": 7.599809050784502e-06, "loss": 0.148, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2994828737750045, "learning_rate": 7.555486488060661e-06, "loss": 0.1714, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.28491194837512657, "learning_rate": 7.511263431335249e-06, "loss": 0.1575, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.28635221564463403, "learning_rate": 7.467140234214656e-06, "loss": 0.1743, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.28135537116502235, "learning_rate": 7.423117249506777e-06, "loss": 0.1568, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.26878957255249486, "learning_rate": 7.379194829218231e-06, "loss": 0.173, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.2764554426079451, "learning_rate": 7.335373324551518e-06, "loss": 0.1503, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.27774007231176123, "learning_rate": 7.291653085902224e-06, "loss": 0.1395, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2790027813311648, "learning_rate": 7.248034462856213e-06, "loss": 0.163, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2846027083094005, "learning_rate": 7.20451780418683e-06, "loss": 0.1565, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2879426373604157, "learning_rate": 7.161103457852128e-06, "loss": 0.1686, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.2973198956578022, "learning_rate": 7.117791770992046e-06, "loss": 0.1617, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.29872640460779093, "learning_rate": 7.074583089925688e-06, "loss": 0.1457, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.2758212849474621, "learning_rate": 7.0314777601485155e-06, "loss": 0.1592, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.27989780432711625, "learning_rate": 6.988476126329604e-06, "loss": 0.1623, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.28528948326412296, "learning_rate": 6.945578532308857e-06, "loss": 0.1525, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.27307496778085716, "learning_rate": 6.902785321094301e-06, "loss": 0.1603, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.2890640185079892, "learning_rate": 6.8600968348593115e-06, "loss": 0.1629, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.27120261739834667, "learning_rate": 6.817513414939892e-06, "loss": 0.1674, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.27862262738659604, "learning_rate": 6.775035401831924e-06, "loss": 0.161, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.2930902469832868, "learning_rate": 6.732663135188473e-06, "loss": 0.1322, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.2890666611602021, "learning_rate": 6.690396953817055e-06, "loss": 0.154, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.27968325270576977, "learning_rate": 6.648237195676927e-06, "loss": 0.1632, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.2789686380557616, "learning_rate": 6.606184197876395e-06, "loss": 0.1516, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.28877888981919314, "learning_rate": 6.564238296670109e-06, "loss": 0.1574, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2966063101959199, "learning_rate": 6.52239982745638e-06, "loss": 0.1705, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.2990576167575563, "learning_rate": 6.480669124774484e-06, "loss": 0.1542, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.2786991729240659, "learning_rate": 6.439046522302013e-06, "loss": 0.1746, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.283167475267291, "learning_rate": 6.397532352852191e-06, "loss": 0.1535, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.27773361874181857, "learning_rate": 6.356126948371202e-06, "loss": 0.1622, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.2939828125384777, "learning_rate": 6.314830639935559e-06, "loss": 0.1421, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2813914092027016, "learning_rate": 6.273643757749448e-06, "loss": 0.1496, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.28254231294833554, "learning_rate": 6.2325666311420856e-06, "loss": 0.1732, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.29601770709859304, "learning_rate": 6.1915995885650675e-06, "loss": 0.1678, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.2744161562393029, "learning_rate": 6.150742957589784e-06, "loss": 0.1241, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.28122954159366814, "learning_rate": 6.109997064904774e-06, "loss": 0.1739, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2904401450366224, "learning_rate": 6.069362236313092e-06, "loss": 0.1787, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2780735983219564, "learning_rate": 6.0288387967297565e-06, "loss": 0.1689, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2751627749654271, "learning_rate": 5.988427070179108e-06, "loss": 0.1468, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2793480102452011, "learning_rate": 5.948127379792234e-06, "loss": 0.1642, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.2765460972032124, "learning_rate": 5.90794004780439e-06, "loss": 0.1451, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.28111789716751256, "learning_rate": 5.867865395552405e-06, "loss": 0.1974, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.2959909115658915, "learning_rate": 5.8279037434721364e-06, "loss": 0.1642, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.2842878736284924, "learning_rate": 5.788055411095892e-06, "loss": 0.1663, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2830490683684816, "learning_rate": 5.7483207170498625e-06, "loss": 0.1812, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.28277207245887087, "learning_rate": 5.708699979051613e-06, "loss": 0.1593, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2813016709070122, "learning_rate": 5.66919351390751e-06, "loss": 0.178, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.2853826874251155, "learning_rate": 5.629801637510188e-06, "loss": 0.1569, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.272779741696073, "learning_rate": 5.590524664836043e-06, "loss": 0.1649, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.2809079410286303, "learning_rate": 5.551362909942708e-06, "loss": 0.1595, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.28560749302838356, "learning_rate": 5.51231668596653e-06, "loss": 0.1715, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.2713034397427249, "learning_rate": 5.47338630512007e-06, "loss": 0.1556, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.26762559979756645, "learning_rate": 5.434572078689617e-06, "loss": 0.159, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.27927185470632476, "learning_rate": 5.395874317032694e-06, "loss": 0.1574, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.2963146258742503, "learning_rate": 5.357293329575573e-06, "loss": 0.1547, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.27852952126766994, "learning_rate": 5.318829424810797e-06, "loss": 0.161, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.2813682877158351, "learning_rate": 5.280482910294728e-06, "loss": 0.1689, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.277935961142721, "learning_rate": 5.242254092645078e-06, "loss": 0.1531, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2708950946687383, "learning_rate": 5.2041432775384445e-06, "loss": 0.1767, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.2874356101335683, "learning_rate": 5.166150769707892e-06, "loss": 0.1522, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.27829750135935755, "learning_rate": 5.128276872940503e-06, "loss": 0.1541, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.2828473982291247, "learning_rate": 5.090521890074953e-06, "loss": 0.1418, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2793414488520428, "learning_rate": 5.0528861229990675e-06, "loss": 0.16, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.2691846813032077, "learning_rate": 5.015369872647442e-06, "loss": 0.1851, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.26296126126263597, "learning_rate": 4.9779734389990195e-06, "loss": 0.189, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.29194695137069626, "learning_rate": 4.940697121074675e-06, "loss": 0.1612, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.2986019611171456, "learning_rate": 4.903541216934864e-06, "loss": 0.1537, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.27747853808773965, "learning_rate": 4.8665060236772e-06, "loss": 0.1545, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2829109519569538, "learning_rate": 4.829591837434102e-06, "loss": 0.1583, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.28545464051651326, "learning_rate": 4.792798953370424e-06, "loss": 0.1442, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.27289775206813793, "learning_rate": 4.756127665681083e-06, "loss": 0.1569, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.27344527317508177, "learning_rate": 4.719578267588725e-06, "loss": 0.1779, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.2668639672977497, "learning_rate": 4.6831510513413525e-06, "loss": 0.1584, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.33977921059659144, "learning_rate": 4.6468463082100176e-06, "loss": 0.1083, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.28829089174877426, "learning_rate": 4.610664328486485e-06, "loss": 0.1224, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.2509506221507859, "learning_rate": 4.5746054014809e-06, "loss": 0.1003, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.22156334372421704, "learning_rate": 4.5386698155194766e-06, "loss": 0.1259, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.2633788065664131, "learning_rate": 4.502857857942204e-06, "loss": 0.128, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.30306478493830236, "learning_rate": 4.467169815100549e-06, "loss": 0.1271, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3198574033264398, "learning_rate": 4.431605972355137e-06, "loss": 0.1264, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.3246406752070377, "learning_rate": 4.396166614073516e-06, "loss": 0.1305, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.2626111138446078, "learning_rate": 4.360852023627846e-06, "loss": 0.1415, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.2497315654612154, "learning_rate": 4.325662483392656e-06, "loss": 0.1022, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2585731024163048, "learning_rate": 4.29059827474257e-06, "loss": 0.1239, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.27689737987216406, "learning_rate": 4.255659678050063e-06, "loss": 0.1298, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.24700325212726493, "learning_rate": 4.22084697268323e-06, "loss": 0.1078, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.24042342228910246, "learning_rate": 4.186160437003535e-06, "loss": 0.1163, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.24267625133743598, "learning_rate": 4.151600348363582e-06, "loss": 0.1232, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.24702039857737187, "learning_rate": 4.11716698310493e-06, "loss": 0.1187, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.22909568863056645, "learning_rate": 4.082860616555848e-06, "loss": 0.1251, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.23453300167622063, "learning_rate": 4.048681523029125e-06, "loss": 0.1063, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2307029069628185, "learning_rate": 4.014629975819882e-06, "loss": 0.1187, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.22432118613359256, "learning_rate": 3.9807062472033855e-06, "loss": 0.1146, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.23342019959111188, "learning_rate": 3.94691060843287e-06, "loss": 0.1111, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.23629614457141507, "learning_rate": 3.913243329737353e-06, "loss": 0.1312, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.22827625274577534, "learning_rate": 3.879704680319503e-06, "loss": 0.1272, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.23333163368132098, "learning_rate": 3.846294928353471e-06, "loss": 0.1161, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.22894511285900987, "learning_rate": 3.8130143409827345e-06, "loss": 0.124, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2180825239808305, "learning_rate": 3.7798631843179887e-06, "loss": 0.0937, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.22951527979093528, "learning_rate": 3.7468417234349973e-06, "loss": 0.1165, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2241558750771541, "learning_rate": 3.7139502223724823e-06, "loss": 0.1279, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.22175609644922445, "learning_rate": 3.6811889441300095e-06, "loss": 0.1103, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.22164317583663443, "learning_rate": 3.648558150665886e-06, "loss": 0.1265, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.22216858931542702, "learning_rate": 3.616058102895075e-06, "loss": 0.1214, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2302538849818666, "learning_rate": 3.583689060687079e-06, "loss": 0.1152, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.22457286458681358, "learning_rate": 3.5514512828639023e-06, "loss": 0.1161, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.22528584423880985, "learning_rate": 3.51934502719796e-06, "loss": 0.1083, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.22527576186112003, "learning_rate": 3.4873705504100185e-06, "loss": 0.1412, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.22670170440648918, "learning_rate": 3.4555281081671345e-06, "loss": 0.1105, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.2183242080504939, "learning_rate": 3.4238179550806326e-06, "loss": 0.1074, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.2281034388856928, "learning_rate": 3.3922403447040497e-06, "loss": 0.1245, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.21354144492433666, "learning_rate": 3.3607955295311247e-06, "loss": 0.1144, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.20138557222883438, "learning_rate": 3.32948376099375e-06, "loss": 0.109, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.2234399553670747, "learning_rate": 3.2983052894599976e-06, "loss": 0.1177, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.22892367922275894, "learning_rate": 3.2672603642320945e-06, "loss": 0.1266, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.21389661724263714, "learning_rate": 3.236349233544438e-06, "loss": 0.113, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.22554823444494035, "learning_rate": 3.205572144561604e-06, "loss": 0.1286, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.22163443688057452, "learning_rate": 3.174929343376374e-06, "loss": 0.1042, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.21636540576039667, "learning_rate": 3.1444210750077777e-06, "loss": 0.1147, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.22267698866210534, "learning_rate": 3.1140475833991046e-06, "loss": 0.1188, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.21711324023894446, "learning_rate": 3.0838091114159895e-06, "loss": 0.1027, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2171233197953307, "learning_rate": 3.0537059008444524e-06, "loss": 0.1134, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.21727946578836285, "learning_rate": 3.0237381923889563e-06, "loss": 0.1093, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.20880201824887482, "learning_rate": 2.9939062256704997e-06, "loss": 0.0915, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.2229125982527681, "learning_rate": 2.964210239224696e-06, "loss": 0.1178, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.21770651667019508, "learning_rate": 2.934650470499869e-06, "loss": 0.1153, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.22026189146346015, "learning_rate": 2.905227155855128e-06, "loss": 0.1241, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.21026904418918899, "learning_rate": 2.875940530558519e-06, "loss": 0.1271, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2172602471075825, "learning_rate": 2.8467908287851154e-06, "loss": 0.1251, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.23607268513250262, "learning_rate": 2.8177782836151603e-06, "loss": 0.1235, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.21588833201974847, "learning_rate": 2.7889031270321874e-06, "loss": 0.1173, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.21618610047421036, "learning_rate": 2.760165589921184e-06, "loss": 0.1057, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.21309495415991178, "learning_rate": 2.7315659020667305e-06, "loss": 0.1238, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21567322920478305, "learning_rate": 2.703104292151164e-06, "loss": 0.1158, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.23175862340372497, "learning_rate": 2.6747809877527607e-06, "loss": 0.1108, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.2249987589233137, "learning_rate": 2.6465962153439082e-06, "loss": 0.1086, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.21888317918870212, "learning_rate": 2.618550200289303e-06, "loss": 0.1142, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.23141354115999557, "learning_rate": 2.59064316684412e-06, "loss": 0.1079, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20686408858988867, "learning_rate": 2.562875338152264e-06, "loss": 0.1181, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2203905753545074, "learning_rate": 2.5352469362445552e-06, "loss": 0.1152, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2167960800301197, "learning_rate": 2.5077581820369523e-06, "loss": 0.1169, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.24476512396495212, "learning_rate": 2.480409295328803e-06, "loss": 0.088, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.21887384155599018, "learning_rate": 2.45320049480108e-06, "loss": 0.1102, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.21721335840487566, "learning_rate": 2.4261319980146293e-06, "loss": 0.1358, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.21999735883432947, "learning_rate": 2.399204021408421e-06, "loss": 0.1214, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.21519764659684149, "learning_rate": 2.3724167802978395e-06, "loss": 0.1065, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.24696786485949754, "learning_rate": 2.3457704888729625e-06, "loss": 0.1274, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.22469937668555282, "learning_rate": 2.3192653601968162e-06, "loss": 0.0982, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.22499590289754628, "learning_rate": 2.2929016062037057e-06, "loss": 0.1081, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.22596878180596608, "learning_rate": 2.2666794376975055e-06, "loss": 0.1153, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.21809170880549691, "learning_rate": 2.24059906434998e-06, "loss": 0.0825, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.21393918349090477, "learning_rate": 2.214660694699091e-06, "loss": 0.1265, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.21531180034620231, "learning_rate": 2.188864536147355e-06, "loss": 0.1242, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.21892323418724008, "learning_rate": 2.1632107949601757e-06, "loss": 0.1168, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.21863026536038524, "learning_rate": 2.137699676264171e-06, "loss": 0.093, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.22688257828569347, "learning_rate": 2.1123313840455738e-06, "loss": 0.1091, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.21700252514063287, "learning_rate": 2.08710612114857e-06, "loss": 0.1239, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.22886328240866163, "learning_rate": 2.0620240892736953e-06, "loss": 0.1121, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.2146468009478975, "learning_rate": 2.0370854889762e-06, "loss": 0.1059, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.2327126733793393, "learning_rate": 2.0122905196644726e-06, "loss": 0.1229, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.22082513645442836, "learning_rate": 1.987639379598427e-06, "loss": 0.1244, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21991484137951992, "learning_rate": 1.963132265887919e-06, "loss": 0.122, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.22307958246438317, "learning_rate": 1.9387693744911784e-06, "loss": 0.1155, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.2231558379385478, "learning_rate": 1.9145509002132368e-06, "loss": 0.1285, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.21831475580379586, "learning_rate": 1.8904770367043723e-06, "loss": 0.125, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.22686204595048237, "learning_rate": 1.8665479764585504e-06, "loss": 0.1231, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2250416315747861, "learning_rate": 1.8427639108118977e-06, "loss": 0.1089, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.20809914330005208, "learning_rate": 1.8191250299411755e-06, "loss": 0.1242, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.21946255543850657, "learning_rate": 1.7956315228622446e-06, "loss": 0.1218, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2171056631814815, "learning_rate": 1.7722835774285553e-06, "loss": 0.0971, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2139473884589527, "learning_rate": 1.7490813803296624e-06, "loss": 0.1062, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.24908960977403652, "learning_rate": 1.726025117089718e-06, "loss": 0.1199, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.21327815642126685, "learning_rate": 1.70311497206598e-06, "loss": 0.111, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2220905710323581, "learning_rate": 1.6803511284473638e-06, "loss": 0.1251, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.2240020703666072, "learning_rate": 1.6577337682529538e-06, "loss": 0.1075, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.21904194451813436, "learning_rate": 1.6352630723305617e-06, "loss": 0.1115, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2205149820990446, "learning_rate": 1.612939220355272e-06, "loss": 0.1175, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.22805251543821853, "learning_rate": 1.5907623908280112e-06, "loss": 0.1135, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2070236593119525, "learning_rate": 1.568732761074121e-06, "loss": 0.1159, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.23052591643363313, "learning_rate": 1.5468505072419237e-06, "loss": 0.106, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.20836741988445004, "learning_rate": 1.5251158043013448e-06, "loss": 0.1209, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2178221301504933, "learning_rate": 1.5035288260424885e-06, "loss": 0.1159, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.22312791677175295, "learning_rate": 1.4820897450742623e-06, "loss": 0.1135, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2152165209697255, "learning_rate": 1.4607987328229767e-06, "loss": 0.1064, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.21445850197358324, "learning_rate": 1.4396559595310056e-06, "loss": 0.1098, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2195735167252188, "learning_rate": 1.4186615942553973e-06, "loss": 0.1067, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2265642583299422, "learning_rate": 1.3978158048665424e-06, "loss": 0.1346, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2179203342544948, "learning_rate": 1.3771187580468115e-06, "loss": 0.1092, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.21485141719551326, "learning_rate": 1.3565706192892392e-06, "loss": 0.1174, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.2255486612319705, "learning_rate": 1.3361715528961993e-06, "loss": 0.1101, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2137443458128996, "learning_rate": 1.3159217219780817e-06, "loss": 0.0984, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.2281043084996544, "learning_rate": 1.2958212884519949e-06, "loss": 0.0956, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.21693498499685526, "learning_rate": 1.2758704130404675e-06, "loss": 0.136, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.22622927322047276, "learning_rate": 1.2560692552701738e-06, "loss": 0.1275, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2368989537775693, "learning_rate": 1.2364179734706382e-06, "loss": 0.0934, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.20933731575067707, "learning_rate": 1.2169167247729852e-06, "loss": 0.1068, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2259907456482138, "learning_rate": 1.1975656651086864e-06, "loss": 0.1087, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.21626354666076938, "learning_rate": 1.1783649492082926e-06, "loss": 0.1165, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.22435705714964532, "learning_rate": 1.1593147306002183e-06, "loss": 0.1193, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2162981344919084, "learning_rate": 1.140415161609505e-06, "loss": 0.0885, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.22019444494565524, "learning_rate": 1.121666393356604e-06, "loss": 0.1302, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.22985059950833975, "learning_rate": 1.1030685757561632e-06, "loss": 0.1195, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.21909839148208726, "learning_rate": 1.0846218575158373e-06, "loss": 0.125, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.21735774085926224, "learning_rate": 1.066326386135097e-06, "loss": 0.1198, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.22481336719357592, "learning_rate": 1.0481823079040398e-06, "loss": 0.1252, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.2165228780214588, "learning_rate": 1.0301897679022344e-06, "loss": 0.097, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.2104866189406838, "learning_rate": 1.0123489099975491e-06, "loss": 0.1235, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2186984792267853, "learning_rate": 9.9465987684501e-07, "loss": 0.1197, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.21769143841821134, "learning_rate": 9.771228098856534e-07, "loss": 0.1178, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.22294627187784455, "learning_rate": 9.597378493454013e-07, "loss": 0.1163, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.2271588548474892, "learning_rate": 9.425051342339353e-07, "loss": 0.129, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.20562819880726974, "learning_rate": 9.254248023435864e-07, "loss": 0.1308, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.224284566700251, "learning_rate": 9.084969902482288e-07, "loss": 0.1369, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.21521107566573885, "learning_rate": 8.917218333021993e-07, "loss": 0.1407, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.22161346578966318, "learning_rate": 8.750994656392109e-07, "loss": 0.1176, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.21057528229418868, "learning_rate": 8.58630020171265e-07, "loss": 0.1136, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.21451763440703317, "learning_rate": 8.423136285876099e-07, "loss": 0.1052, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.22462253224047357, "learning_rate": 8.26150421353682e-07, "loss": 0.1367, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.22478721912154978, "learning_rate": 8.101405277100549e-07, "loss": 0.1206, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.21313726117784396, "learning_rate": 7.942840756714077e-07, "loss": 0.1027, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.21292432815675955, "learning_rate": 7.785811920255093e-07, "loss": 0.1408, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.21320748891840213, "learning_rate": 7.630320023322024e-07, "loss": 0.1206, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.21713031580833683, "learning_rate": 7.476366309223903e-07, "loss": 0.1087, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.21730304256409547, "learning_rate": 7.323952008970537e-07, "loss": 0.1211, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.20728941304357057, "learning_rate": 7.173078341262618e-07, "loss": 0.1005, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2220395846015751, "learning_rate": 7.023746512481989e-07, "loss": 0.1131, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2156477075228908, "learning_rate": 6.875957716681902e-07, "loss": 0.1071, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.21111920419303234, "learning_rate": 6.729713135577687e-07, "loss": 0.1297, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.21960131305977001, "learning_rate": 6.585013938537143e-07, "loss": 0.1111, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.22150810646065805, "learning_rate": 6.441861282571115e-07, "loss": 0.1055, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.2137144191352296, "learning_rate": 6.300256312324471e-07, "loss": 0.1111, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.21372904500454634, "learning_rate": 6.160200160066776e-07, "loss": 0.1034, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.21579482598097488, "learning_rate": 6.021693945683327e-07, "loss": 0.1114, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.22546282939275308, "learning_rate": 5.884738776666044e-07, "loss": 0.1228, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.21503051190661593, "learning_rate": 5.749335748104878e-07, "loss": 0.1209, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.22468244675541668, "learning_rate": 5.615485942678778e-07, "loss": 0.1456, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.21620073639012935, "learning_rate": 5.483190430647289e-07, "loss": 0.1208, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.22542272151740034, "learning_rate": 5.352450269841747e-07, "loss": 0.1175, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.22530862089315323, "learning_rate": 5.22326650565701e-07, "loss": 0.1074, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2177629864605589, "learning_rate": 5.095640171043048e-07, "loss": 0.101, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.208010589221903, "learning_rate": 4.969572286496594e-07, "loss": 0.1167, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.211527954383882, "learning_rate": 4.845063860053079e-07, "loss": 0.1136, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.21888347288406385, "learning_rate": 4.7221158872785997e-07, "loss": 0.104, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.22619080304412484, "learning_rate": 4.600729351261857e-07, "loss": 0.1195, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.23351676122914333, "learning_rate": 4.4809052226063355e-07, "loss": 0.1099, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.24352426020195544, "learning_rate": 4.3626444594226046e-07, "loss": 0.12, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2247033661734468, "learning_rate": 4.245948007320588e-07, "loss": 0.137, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.20733429125682512, "learning_rate": 4.130816799401971e-07, "loss": 0.115, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.20993114602807875, "learning_rate": 4.017251756252827e-07, "loss": 0.1117, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.21569924532405735, "learning_rate": 3.9052537859362473e-07, "loss": 0.1013, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.22179591668954685, "learning_rate": 3.7948237839849687e-07, "loss": 0.128, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.21574441011824427, "learning_rate": 3.6859626333943797e-07, "loss": 0.1119, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.22218590193334015, "learning_rate": 3.578671204615347e-07, "loss": 0.1191, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.2228411174962325, "learning_rate": 3.472950355547267e-07, "loss": 0.1195, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.20514417281127323, "learning_rate": 3.3688009315312244e-07, "loss": 0.1216, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.22919470193312838, "learning_rate": 3.266223765343224e-07, "loss": 0.1134, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.21147075637594784, "learning_rate": 3.16521967718757e-07, "loss": 0.1199, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.21486073767279953, "learning_rate": 3.0657894746902726e-07, "loss": 0.1144, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.21871698051576635, "learning_rate": 2.9679339528925654e-07, "loss": 0.1186, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.21812557224761064, "learning_rate": 2.871653894244597e-07, "loss": 0.1057, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.21015662752633113, "learning_rate": 2.7769500685991266e-07, "loss": 0.1484, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.21131048481513565, "learning_rate": 2.683823233205485e-07, "loss": 0.104, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.2316667602098268, "learning_rate": 2.592274132703287e-07, "loss": 0.1185, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.2191254818446028, "learning_rate": 2.502303499116754e-07, "loss": 0.1082, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.21071172110129513, "learning_rate": 2.413912051848666e-07, "loss": 0.1133, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.20992820997984482, "learning_rate": 2.3271004976746613e-07, "loss": 0.1121, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2100181980580389, "learning_rate": 2.2418695307376393e-07, "loss": 0.1136, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2145329944104384, "learning_rate": 2.1582198325420968e-07, "loss": 0.1227, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.21330194780340733, "learning_rate": 2.0761520719488447e-07, "loss": 0.1138, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.2180186151896674, "learning_rate": 1.9956669051694798e-07, "loss": 0.1256, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.2164750235562713, "learning_rate": 1.916764975761254e-07, "loss": 0.1234, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.21772892652617948, "learning_rate": 1.839446914621923e-07, "loss": 0.1219, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.21348067393882064, "learning_rate": 1.7637133399845962e-07, "loss": 0.141, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.23366729590537588, "learning_rate": 1.6895648574129397e-07, "loss": 0.111, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.22312642633784022, "learning_rate": 1.6170020597962465e-07, "loss": 0.1213, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.20851076212235642, "learning_rate": 1.5460255273447078e-07, "loss": 0.1144, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.21888884335119985, "learning_rate": 1.4766358275847715e-07, "loss": 0.1227, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.21971248533177418, "learning_rate": 1.4088335153546573e-07, "loss": 0.1144, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.21763016781975353, "learning_rate": 1.3426191327998496e-07, "loss": 0.1093, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.21760006561940917, "learning_rate": 1.277993209368744e-07, "loss": 0.1424, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.21536020260509314, "learning_rate": 1.214956261808542e-07, "loss": 0.1271, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.2224387230408578, "learning_rate": 1.1535087941609846e-07, "loss": 0.1319, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.1913599318840531, "learning_rate": 1.0936512977583802e-07, "loss": 0.1027, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.21769668795614391, "learning_rate": 1.0353842512196732e-07, "loss": 0.1154, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.21521356184056628, "learning_rate": 9.787081204466253e-08, "loss": 0.1399, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.21535982593494715, "learning_rate": 9.236233586200627e-08, "loss": 0.1246, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.22913480976286385, "learning_rate": 8.70130406196279e-08, "loss": 0.0768, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2298151390387868, "learning_rate": 8.182296909035047e-08, "loss": 0.1202, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.21474671621156322, "learning_rate": 7.679216277384439e-08, "loss": 0.116, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.21414804513735644, "learning_rate": 7.19206618963053e-08, "loss": 0.105, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.2187971836812536, "learning_rate": 6.720850541012347e-08, "loss": 0.141, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.21439165670019192, "learning_rate": 6.265573099357714e-08, "loss": 0.1227, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.20805478688372694, "learning_rate": 5.826237505053067e-08, "loss": 0.1171, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.21380600193041205, "learning_rate": 5.4028472710137e-08, "loss": 0.1294, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.21716589516866, "learning_rate": 4.9954057826571146e-08, "loss": 0.103, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2116348660914453, "learning_rate": 4.6039162978743776e-08, "loss": 0.1321, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.22347956527731624, "learning_rate": 4.228381947004812e-08, "loss": 0.1264, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.21984411645922977, "learning_rate": 3.868805732811343e-08, "loss": 0.1212, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.23746686036292694, "learning_rate": 3.525190530455636e-08, "loss": 0.1136, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.22047338028563004, "learning_rate": 3.197539087475887e-08, "loss": 0.1014, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2069107826463759, "learning_rate": 2.8858540237641786e-08, "loss": 0.1155, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.20509670405415076, "learning_rate": 2.5901378315458247e-08, "loss": 0.133, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.20830819048722699, "learning_rate": 2.3103928753598347e-08, "loss": 0.1115, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.2160161915522125, "learning_rate": 2.0466213920393718e-08, "loss": 0.1353, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.20395557594465957, "learning_rate": 1.7988254906942115e-08, "loss": 0.105, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.21270731429921338, "learning_rate": 1.5670071526936447e-08, "loss": 0.1155, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.21655977814769298, "learning_rate": 1.3511682316509344e-08, "loss": 0.1418, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.22090939332615192, "learning_rate": 1.1513104534086605e-08, "loss": 0.1297, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.21974312906635912, "learning_rate": 9.67435416023843e-09, "loss": 0.1213, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.2169708696879731, "learning_rate": 7.995445897566178e-09, "loss": 0.1152, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.20939495901034716, "learning_rate": 6.476393170578021e-09, "loss": 0.1235, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.2251462445304899, "learning_rate": 5.11720812557348e-09, "loss": 0.0957, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.21937265805198916, "learning_rate": 3.917901630563492e-09, "loss": 0.1197, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.21272572214430321, "learning_rate": 2.878483275170485e-09, "loss": 0.114, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.21858108424819936, "learning_rate": 1.998961370555108e-09, "loss": 0.0929, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.224395524311798, "learning_rate": 1.2793429493518361e-09, "loss": 0.1142, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.22020163100442344, "learning_rate": 7.196337656112384e-10, "loss": 0.1297, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.2280896535551779, "learning_rate": 3.198382947511292e-10, "loss": 0.1066, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.21911132912532014, "learning_rate": 7.995973352770137e-11, "loss": 0.1127, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.2067503343426324, "learning_rate": 0.0, "loss": 0.1089, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.6116754450596495e+18, "train_loss": 0.2824884724339493, "train_runtime": 21501.2629, "train_samples_per_second": 7.348, "train_steps_per_second": 0.057 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.6116754450596495e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }