{ "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": 6.825054419541177, "learning_rate": 3.2258064516129035e-07, "loss": 1.0569, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.748828460364182, "learning_rate": 6.451612903225807e-07, "loss": 1.0711, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.866076199664078, "learning_rate": 9.67741935483871e-07, "loss": 1.1022, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.470918605874541, "learning_rate": 1.2903225806451614e-06, "loss": 1.0836, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.355010297929228, "learning_rate": 1.6129032258064516e-06, "loss": 1.1214, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.217295167536065, "learning_rate": 1.935483870967742e-06, "loss": 1.0772, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.123067441827934, "learning_rate": 2.2580645161290324e-06, "loss": 1.0214, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.722743334740106, "learning_rate": 2.580645161290323e-06, "loss": 0.995, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.6110757093978743, "learning_rate": 2.903225806451613e-06, "loss": 0.9465, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.32780380323199, "learning_rate": 3.225806451612903e-06, "loss": 0.9075, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.2686387772901755, "learning_rate": 3.548387096774194e-06, "loss": 0.9451, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.184038642757368, "learning_rate": 3.870967741935484e-06, "loss": 0.9291, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.648484330147914, "learning_rate": 4.193548387096774e-06, "loss": 0.9673, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.142462885088233, "learning_rate": 4.516129032258065e-06, "loss": 0.9013, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.162285882105991, "learning_rate": 4.838709677419355e-06, "loss": 0.9155, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.091723626686641, "learning_rate": 5.161290322580646e-06, "loss": 0.8966, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 3.0599393594888102, "learning_rate": 5.483870967741935e-06, "loss": 0.8783, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.7179174795003394, "learning_rate": 5.806451612903226e-06, "loss": 0.8596, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.491332369748295, "learning_rate": 6.129032258064517e-06, "loss": 0.8778, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 2.0918841281346525, "learning_rate": 6.451612903225806e-06, "loss": 0.8216, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.7546232621569973, "learning_rate": 6.774193548387097e-06, "loss": 0.8239, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.698047829881821, "learning_rate": 7.096774193548388e-06, "loss": 0.7891, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.7705576194131847, "learning_rate": 7.4193548387096784e-06, "loss": 0.7813, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.8095752928265068, "learning_rate": 7.741935483870968e-06, "loss": 0.7963, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.5894622508156075, "learning_rate": 8.064516129032258e-06, "loss": 0.7702, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.2910733096275098, "learning_rate": 8.387096774193549e-06, "loss": 0.8113, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.19767913898592, "learning_rate": 8.70967741935484e-06, "loss": 0.7793, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.3873510277674892, "learning_rate": 9.03225806451613e-06, "loss": 0.7927, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.1092059274070623, "learning_rate": 9.35483870967742e-06, "loss": 0.7528, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.0151191038222867, "learning_rate": 9.67741935483871e-06, "loss": 0.7738, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.992601551948264, "learning_rate": 1e-05, "loss": 0.7266, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.8537146442716067, "learning_rate": 1.0322580645161291e-05, "loss": 0.7709, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.793432580802079, "learning_rate": 1.0645161290322582e-05, "loss": 0.7602, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7599824801285324, "learning_rate": 1.096774193548387e-05, "loss": 0.7296, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.7094734023291569, "learning_rate": 1.1290322580645164e-05, "loss": 0.7287, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.7295758537999489, "learning_rate": 1.1612903225806453e-05, "loss": 0.7326, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.7056821909918284, "learning_rate": 1.1935483870967743e-05, "loss": 0.7269, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6746238819001044, "learning_rate": 1.2258064516129034e-05, "loss": 0.7204, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.7504838623590705, "learning_rate": 1.2580645161290324e-05, "loss": 0.7405, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6897125099087856, "learning_rate": 1.2903225806451613e-05, "loss": 0.7111, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.6993508200728078, "learning_rate": 1.3225806451612903e-05, "loss": 0.7303, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6609672854851079, "learning_rate": 1.3548387096774194e-05, "loss": 0.7146, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.6267250958863396, "learning_rate": 1.3870967741935486e-05, "loss": 0.685, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6480950921354333, "learning_rate": 1.4193548387096776e-05, "loss": 0.7528, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.7123265847849674, "learning_rate": 1.4516129032258066e-05, "loss": 0.731, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.6815816942657963, "learning_rate": 1.4838709677419357e-05, "loss": 0.7136, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.7062826234914544, "learning_rate": 1.5161290322580646e-05, "loss": 0.7302, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.6507363589263553, "learning_rate": 1.5483870967741936e-05, "loss": 0.6873, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.7812809901318305, "learning_rate": 1.5806451612903226e-05, "loss": 0.7236, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.8092560047643306, "learning_rate": 1.6129032258064517e-05, "loss": 0.685, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.7323763735596353, "learning_rate": 1.6451612903225807e-05, "loss": 0.7037, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.8408612635348112, "learning_rate": 1.6774193548387098e-05, "loss": 0.7046, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.7546892442135464, "learning_rate": 1.7096774193548388e-05, "loss": 0.6946, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.6535001346296934, "learning_rate": 1.741935483870968e-05, "loss": 0.7014, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7060642280146413, "learning_rate": 1.774193548387097e-05, "loss": 0.683, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6354962347137614, "learning_rate": 1.806451612903226e-05, "loss": 0.7097, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.7156672924206372, "learning_rate": 1.838709677419355e-05, "loss": 0.6951, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6556746727291284, "learning_rate": 1.870967741935484e-05, "loss": 0.6921, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.633537486681799, "learning_rate": 1.903225806451613e-05, "loss": 0.6726, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.6531107328692649, "learning_rate": 1.935483870967742e-05, "loss": 0.6901, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.6881538565781541, "learning_rate": 1.967741935483871e-05, "loss": 0.6914, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.6828097691163163, "learning_rate": 2e-05, "loss": 0.6687, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6791161982989902, "learning_rate": 2.0322580645161292e-05, "loss": 0.6689, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.714241388446567, "learning_rate": 2.0645161290322582e-05, "loss": 0.7012, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.7068480190979938, "learning_rate": 2.0967741935483873e-05, "loss": 0.6729, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.7184343715506439, "learning_rate": 2.1290322580645163e-05, "loss": 0.6552, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7321919269133942, "learning_rate": 2.161290322580645e-05, "loss": 0.6877, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.8025283191621738, "learning_rate": 2.193548387096774e-05, "loss": 0.6835, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.7387087969391107, "learning_rate": 2.225806451612903e-05, "loss": 0.6657, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.9582114693492876, "learning_rate": 2.2580645161290328e-05, "loss": 0.701, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7164028800949761, "learning_rate": 2.2903225806451615e-05, "loss": 0.722, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.8998151489537386, "learning_rate": 2.3225806451612906e-05, "loss": 0.6823, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.8313319070287611, "learning_rate": 2.3548387096774196e-05, "loss": 0.688, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.874189334477062, "learning_rate": 2.3870967741935486e-05, "loss": 0.685, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.8361952770019114, "learning_rate": 2.4193548387096777e-05, "loss": 0.6807, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.7948667100967238, "learning_rate": 2.4516129032258067e-05, "loss": 0.6913, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.0497062980197516, "learning_rate": 2.4838709677419358e-05, "loss": 0.7203, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7251772835961582, "learning_rate": 2.5161290322580648e-05, "loss": 0.645, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8851111308096445, "learning_rate": 2.548387096774194e-05, "loss": 0.6795, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.9382716134132101, "learning_rate": 2.5806451612903226e-05, "loss": 0.6822, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.8070967032217033, "learning_rate": 2.6129032258064516e-05, "loss": 0.6588, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.9852571305033545, "learning_rate": 2.6451612903225806e-05, "loss": 0.6696, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8888572484214702, "learning_rate": 2.6774193548387097e-05, "loss": 0.6869, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 1.0149938258119413, "learning_rate": 2.7096774193548387e-05, "loss": 0.6823, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.9551046209747865, "learning_rate": 2.7419354838709678e-05, "loss": 0.6912, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.8517170855763943, "learning_rate": 2.774193548387097e-05, "loss": 0.6766, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 1.1820625606317656, "learning_rate": 2.8064516129032262e-05, "loss": 0.6938, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.6872907417017746, "learning_rate": 2.8387096774193552e-05, "loss": 0.6547, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.0760805334982873, "learning_rate": 2.8709677419354843e-05, "loss": 0.6647, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 1.066898273646577, "learning_rate": 2.9032258064516133e-05, "loss": 0.6741, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.0865540015791917, "learning_rate": 2.9354838709677423e-05, "loss": 0.6709, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.8077914557465333, "learning_rate": 2.9677419354838714e-05, "loss": 0.6317, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.1791296554365325, "learning_rate": 3.0000000000000004e-05, "loss": 0.6749, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.805545520602745, "learning_rate": 3.032258064516129e-05, "loss": 0.6597, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.8036892173165352, "learning_rate": 3.0645161290322585e-05, "loss": 0.6591, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.8480747612710238, "learning_rate": 3.096774193548387e-05, "loss": 0.6629, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.7003082649935244, "learning_rate": 3.1290322580645166e-05, "loss": 0.6497, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.8555146810681135, "learning_rate": 3.161290322580645e-05, "loss": 0.6653, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.7868861417589315, "learning_rate": 3.193548387096774e-05, "loss": 0.664, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.762135896186569, "learning_rate": 3.2258064516129034e-05, "loss": 0.6668, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.1031983229808435, "learning_rate": 3.258064516129033e-05, "loss": 0.6681, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.869790110470581, "learning_rate": 3.2903225806451614e-05, "loss": 0.6802, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.9735559706426985, "learning_rate": 3.322580645161291e-05, "loss": 0.6452, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.2282427258827124, "learning_rate": 3.3548387096774195e-05, "loss": 0.6788, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.7169667842622522, "learning_rate": 3.387096774193549e-05, "loss": 0.6638, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.2904346723522295, "learning_rate": 3.4193548387096776e-05, "loss": 0.6752, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.6895985479973245, "learning_rate": 3.451612903225807e-05, "loss": 0.6491, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.9910171897078907, "learning_rate": 3.483870967741936e-05, "loss": 0.6626, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9107733116549726, "learning_rate": 3.516129032258065e-05, "loss": 0.6554, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.6663531826317092, "learning_rate": 3.548387096774194e-05, "loss": 0.6404, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.7736810839100637, "learning_rate": 3.5806451612903225e-05, "loss": 0.6697, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.0002245335934061, "learning_rate": 3.612903225806452e-05, "loss": 0.6831, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.9736793204384966, "learning_rate": 3.6451612903225805e-05, "loss": 0.6721, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.775380912487795, "learning_rate": 3.67741935483871e-05, "loss": 0.6306, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.9853490457526016, "learning_rate": 3.7096774193548386e-05, "loss": 0.6357, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6729556255430529, "learning_rate": 3.741935483870968e-05, "loss": 0.6166, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.9495394831204231, "learning_rate": 3.7741935483870974e-05, "loss": 0.669, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.9530898269056566, "learning_rate": 3.806451612903226e-05, "loss": 0.6553, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.8277183083401092, "learning_rate": 3.8387096774193555e-05, "loss": 0.6665, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.8198965176994983, "learning_rate": 3.870967741935484e-05, "loss": 0.645, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.8744140313636305, "learning_rate": 3.9032258064516135e-05, "loss": 0.6804, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.7401076879381911, "learning_rate": 3.935483870967742e-05, "loss": 0.6146, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.9181238369701616, "learning_rate": 3.9677419354838716e-05, "loss": 0.664, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7511027370837902, "learning_rate": 4e-05, "loss": 0.6471, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.7683175753048519, "learning_rate": 3.9999920040266474e-05, "loss": 0.6025, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.8033654006365464, "learning_rate": 3.999968016170525e-05, "loss": 0.6471, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.7079238607730387, "learning_rate": 3.9999280366234394e-05, "loss": 0.661, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.7299488741338442, "learning_rate": 3.999872065705065e-05, "loss": 0.6617, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.6812248009308853, "learning_rate": 3.999800103862945e-05, "loss": 0.6427, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6721790614317281, "learning_rate": 3.9997121516724834e-05, "loss": 0.6425, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.6899149118361745, "learning_rate": 3.999608209836944e-05, "loss": 0.6849, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.6253711209882717, "learning_rate": 3.999488279187443e-05, "loss": 0.6424, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.700042163634394, "learning_rate": 3.9993523606829425e-05, "loss": 0.6346, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.5982880386985315, "learning_rate": 3.9992004554102435e-05, "loss": 0.6532, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.6162133951019279, "learning_rate": 3.999032564583976e-05, "loss": 0.6221, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.7551423226220295, "learning_rate": 3.998848689546591e-05, "loss": 0.662, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7186544138251635, "learning_rate": 3.9986488317683496e-05, "loss": 0.6526, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.6898153210672242, "learning_rate": 3.9984329928473067e-05, "loss": 0.6655, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.6553659905694444, "learning_rate": 3.998201174509306e-05, "loss": 0.6321, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6523345847662466, "learning_rate": 3.997953378607961e-05, "loss": 0.6296, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6028260597744434, "learning_rate": 3.9976896071246403e-05, "loss": 0.6315, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.7318302895126878, "learning_rate": 3.997409862168454e-05, "loss": 0.6526, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.7256547385851411, "learning_rate": 3.997114145976237e-05, "loss": 0.6664, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.6178424351086572, "learning_rate": 3.9968024609125245e-05, "loss": 0.6676, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7290326077217759, "learning_rate": 3.996474809469545e-05, "loss": 0.6811, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.8170106004871639, "learning_rate": 3.996131194267189e-05, "loss": 0.6542, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.6953729157585294, "learning_rate": 3.995771618052995e-05, "loss": 0.6229, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.7059564012589662, "learning_rate": 3.9953960837021256e-05, "loss": 0.6348, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7293945639172101, "learning_rate": 3.995004594217343e-05, "loss": 0.6355, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6592851857333282, "learning_rate": 3.994597152728987e-05, "loss": 0.6527, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.7943206099465042, "learning_rate": 3.994173762494947e-05, "loss": 0.6366, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6863592037687501, "learning_rate": 3.9937344269006424e-05, "loss": 0.6576, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7667029691163726, "learning_rate": 3.993279149458988e-05, "loss": 0.656, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.80807192260491, "learning_rate": 3.9928079338103695e-05, "loss": 0.6336, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.6433469582621506, "learning_rate": 3.992320783722616e-05, "loss": 0.6577, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7352919653764202, "learning_rate": 3.991817703090965e-05, "loss": 0.5959, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6279058817675248, "learning_rate": 3.991298695938038e-05, "loss": 0.6361, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6472549437188947, "learning_rate": 3.9907637664138e-05, "loss": 0.656, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6700551451708687, "learning_rate": 3.990212918795534e-05, "loss": 0.6635, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.663146835816161, "learning_rate": 3.9896461574878036e-05, "loss": 0.6283, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6771738146230998, "learning_rate": 3.989063487022416e-05, "loss": 0.6444, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.6385366173569105, "learning_rate": 3.9884649120583903e-05, "loss": 0.62, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.6451911981137679, "learning_rate": 3.987850437381915e-05, "loss": 0.6475, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.7345983048220407, "learning_rate": 3.987220067906313e-05, "loss": 0.6651, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.6371070563194006, "learning_rate": 3.986573808672002e-05, "loss": 0.648, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6402701101805014, "learning_rate": 3.9859116648464534e-05, "loss": 0.5978, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.6403912020302122, "learning_rate": 3.985233641724152e-05, "loss": 0.642, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.578233884244989, "learning_rate": 3.984539744726554e-05, "loss": 0.6344, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.5921100885758408, "learning_rate": 3.983829979402038e-05, "loss": 0.6522, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.6270285448426739, "learning_rate": 3.983104351425871e-05, "loss": 0.6513, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.5220008778875072, "learning_rate": 3.982362866600154e-05, "loss": 0.6252, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6456721910163464, "learning_rate": 3.9816055308537806e-05, "loss": 0.6364, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.5512644610996306, "learning_rate": 3.980832350242388e-05, "loss": 0.6334, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.7307895881022204, "learning_rate": 3.980043330948306e-05, "loss": 0.6344, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.5911245770573461, "learning_rate": 3.9792384792805124e-05, "loss": 0.6273, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.7355432514289864, "learning_rate": 3.978417801674579e-05, "loss": 0.6281, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.6468034515594016, "learning_rate": 3.9775813046926244e-05, "loss": 0.6728, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6609294383128411, "learning_rate": 3.976728995023254e-05, "loss": 0.6306, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6161965355611005, "learning_rate": 3.975860879481514e-05, "loss": 0.6317, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.5711481157703729, "learning_rate": 3.974976965008833e-05, "loss": 0.6138, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.6048513786578505, "learning_rate": 3.9740772586729674e-05, "loss": 0.6351, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.5629341742306188, "learning_rate": 3.973161767667946e-05, "loss": 0.6157, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6628438746680942, "learning_rate": 3.972230499314009e-05, "loss": 0.6347, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.5322741539728433, "learning_rate": 3.9712834610575545e-05, "loss": 0.6015, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.676056265669429, "learning_rate": 3.9703206604710746e-05, "loss": 0.6485, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.5098235597919433, "learning_rate": 3.969342105253098e-05, "loss": 0.6029, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.769104741778942, "learning_rate": 3.9683478032281246e-05, "loss": 0.6441, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5730743826777702, "learning_rate": 3.967337762346568e-05, "loss": 0.6528, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.8931754179340559, "learning_rate": 3.9663119906846885e-05, "loss": 0.602, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5920798807943299, "learning_rate": 3.965270496444528e-05, "loss": 0.616, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.7895311714473408, "learning_rate": 3.9642132879538465e-05, "loss": 0.6231, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.6812487182993201, "learning_rate": 3.9631403736660566e-05, "loss": 0.6082, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.6104115570371961, "learning_rate": 3.962051762160151e-05, "loss": 0.6366, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.6315334316287621, "learning_rate": 3.960947462140638e-05, "loss": 0.6277, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5779839591863893, "learning_rate": 3.959827482437472e-05, "loss": 0.623, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.6741317204755708, "learning_rate": 3.958691832005981e-05, "loss": 0.6377, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.6176748379798996, "learning_rate": 3.9575405199267944e-05, "loss": 0.6236, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.6834318450022261, "learning_rate": 3.956373555405774e-05, "loss": 0.6173, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6034314975034735, "learning_rate": 3.955190947773937e-05, "loss": 0.608, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.6516729852384622, "learning_rate": 3.9539927064873824e-05, "loss": 0.646, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.649992666190815, "learning_rate": 3.952778841127214e-05, "loss": 0.6386, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5569801967584439, "learning_rate": 3.95154936139947e-05, "loss": 0.6488, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.6590622559038186, "learning_rate": 3.950304277135034e-05, "loss": 0.6198, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.5320648159054102, "learning_rate": 3.94904359828957e-05, "loss": 0.5947, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.570564750679294, "learning_rate": 3.94776733494343e-05, "loss": 0.5909, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.6581926137294171, "learning_rate": 3.9464754973015826e-05, "loss": 0.6381, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5037273393718287, "learning_rate": 3.9451680956935275e-05, "loss": 0.624, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.6068387497150732, "learning_rate": 3.943845140573213e-05, "loss": 0.6192, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.543602468339401, "learning_rate": 3.942506642518952e-05, "loss": 0.6174, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.49907620893209187, "learning_rate": 3.9411526122333396e-05, "loss": 0.6213, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.531107761894581, "learning_rate": 3.939783060543167e-05, "loss": 0.608, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5358964228812046, "learning_rate": 3.938397998399333e-05, "loss": 0.6289, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.5770868429496929, "learning_rate": 3.936997436876756e-05, "loss": 0.6095, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.5693259941168132, "learning_rate": 3.935581387174289e-05, "loss": 0.6427, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.518430456430404, "learning_rate": 3.9341498606146295e-05, "loss": 0.5971, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.5526804491723842, "learning_rate": 3.932702868644224e-05, "loss": 0.6253, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5883314676587269, "learning_rate": 3.931240422833181e-05, "loss": 0.6271, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.6145300686536546, "learning_rate": 3.9297625348751806e-05, "loss": 0.6227, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.8059778818948805, "learning_rate": 3.9282692165873744e-05, "loss": 0.6137, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.6441964902776727, "learning_rate": 3.9267604799102945e-05, "loss": 0.5831, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.693803718350621, "learning_rate": 3.9252363369077615e-05, "loss": 0.5948, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.6609395481776401, "learning_rate": 3.9236967997667796e-05, "loss": 0.5878, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.6874661441480435, "learning_rate": 3.9221418807974496e-05, "loss": 0.6008, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.7296906081253954, "learning_rate": 3.92057159243286e-05, "loss": 0.5911, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.7090046266987414, "learning_rate": 3.9189859472289956e-05, "loss": 0.621, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6345737119244812, "learning_rate": 3.9173849578646324e-05, "loss": 0.5811, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.7247198911859922, "learning_rate": 3.9157686371412395e-05, "loss": 0.6144, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.6863619238233167, "learning_rate": 3.914136997982874e-05, "loss": 0.6277, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.6518001607328672, "learning_rate": 3.912490053436079e-05, "loss": 0.5865, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5774772756960711, "learning_rate": 3.9108278166697805e-05, "loss": 0.6083, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.6797583340607553, "learning_rate": 3.909150300975178e-05, "loss": 0.6053, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.5610247966112113, "learning_rate": 3.907457519765642e-05, "loss": 0.6365, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.6735132785313978, "learning_rate": 3.905749486576607e-05, "loss": 0.6244, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6197011716678292, "learning_rate": 3.90402621506546e-05, "loss": 0.5952, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5439834892316993, "learning_rate": 3.902287719011435e-05, "loss": 0.6039, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.6424282465281079, "learning_rate": 3.900534012315499e-05, "loss": 0.6203, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5530715137426263, "learning_rate": 3.8987651090002454e-05, "loss": 0.6281, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7294082780770326, "learning_rate": 3.896981023209777e-05, "loss": 0.5901, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.614960446224674, "learning_rate": 3.8951817692095966e-05, "loss": 0.5857, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5873781915033057, "learning_rate": 3.893367361386491e-05, "loss": 0.6058, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.5216712695017468, "learning_rate": 3.891537814248417e-05, "loss": 0.6078, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.617228995707405, "learning_rate": 3.889693142424384e-05, "loss": 0.609, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5025428229056682, "learning_rate": 3.8878333606643405e-05, "loss": 0.6039, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.5085459209583583, "learning_rate": 3.885958483839049e-05, "loss": 0.5965, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.6193682502943999, "learning_rate": 3.8840685269399786e-05, "loss": 0.6228, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.49929896402868734, "learning_rate": 3.882163505079171e-05, "loss": 0.6192, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5770085663320852, "learning_rate": 3.880243433489132e-05, "loss": 0.6157, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.7245255889675253, "learning_rate": 3.878308327522702e-05, "loss": 0.5116, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.6043470817029644, "learning_rate": 3.876358202652936e-05, "loss": 0.5086, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.6978899442109613, "learning_rate": 3.8743930744729835e-05, "loss": 0.4813, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6582070651251547, "learning_rate": 3.8724129586959535e-05, "loss": 0.4821, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5720429916105384, "learning_rate": 3.870417871154801e-05, "loss": 0.469, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6901018281967934, "learning_rate": 3.868407827802192e-05, "loss": 0.4784, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5750168250529619, "learning_rate": 3.8663828447103804e-05, "loss": 0.5135, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6235612806933526, "learning_rate": 3.8643429380710765e-05, "loss": 0.486, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6234356897178687, "learning_rate": 3.862288124195319e-05, "loss": 0.4617, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.6548096125109318, "learning_rate": 3.8602184195133464e-05, "loss": 0.4882, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.6851930853310036, "learning_rate": 3.8581338405744604e-05, "loss": 0.4938, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.6072972142704507, "learning_rate": 3.8560344040468996e-05, "loss": 0.5005, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.6183780354720496, "learning_rate": 3.853920126717703e-05, "loss": 0.4683, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6092379555152442, "learning_rate": 3.851791025492574e-05, "loss": 0.5043, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.6718461480726302, "learning_rate": 3.8496471173957515e-05, "loss": 0.4845, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.563666843386439, "learning_rate": 3.847488419569866e-05, "loss": 0.4668, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5610680418197256, "learning_rate": 3.8453149492758077e-05, "loss": 0.4726, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6322685061460364, "learning_rate": 3.8431267238925886e-05, "loss": 0.495, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5556357872160949, "learning_rate": 3.840923760917199e-05, "loss": 0.478, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5690297036329874, "learning_rate": 3.838706077964473e-05, "loss": 0.472, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.5741106014005777, "learning_rate": 3.836473692766944e-05, "loss": 0.4949, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5845184586914142, "learning_rate": 3.834226623174705e-05, "loss": 0.4864, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.5712932225692079, "learning_rate": 3.831964887155264e-05, "loss": 0.479, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.5378933774618633, "learning_rate": 3.829688502793403e-05, "loss": 0.4532, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.6850033587554336, "learning_rate": 3.827397488291029e-05, "loss": 0.5134, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.4901142936232781, "learning_rate": 3.8250918619670343e-05, "loss": 0.496, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.6582632340740203, "learning_rate": 3.822771642257145e-05, "loss": 0.5057, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.536835744662483, "learning_rate": 3.820436847713776e-05, "loss": 0.4916, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.5172241243105896, "learning_rate": 3.8180874970058826e-05, "loss": 0.4636, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.6342438652040471, "learning_rate": 3.8157236089188103e-05, "loss": 0.473, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.48624267529736687, "learning_rate": 3.813345202354145e-05, "loss": 0.4921, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6609050238833264, "learning_rate": 3.810952296329563e-05, "loss": 0.488, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.5680780270305074, "learning_rate": 3.808544909978676e-05, "loss": 0.4795, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.770873202036507, "learning_rate": 3.806123062550882e-05, "loss": 0.4856, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.518293753243077, "learning_rate": 3.803686773411208e-05, "loss": 0.4976, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.579014382864165, "learning_rate": 3.801236062040158e-05, "loss": 0.5, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.46337124889465203, "learning_rate": 3.798770948033553e-05, "loss": 0.4816, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5784022110770736, "learning_rate": 3.796291451102381e-05, "loss": 0.4907, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.4671218702870521, "learning_rate": 3.793797591072631e-05, "loss": 0.4759, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.5313910467439543, "learning_rate": 3.791289387885144e-05, "loss": 0.5153, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4992922707433379, "learning_rate": 3.788766861595443e-05, "loss": 0.4695, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5094025680939922, "learning_rate": 3.7862300323735835e-05, "loss": 0.4907, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.4999183527555996, "learning_rate": 3.783678920503983e-05, "loss": 0.496, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.4807562028721832, "learning_rate": 3.781113546385265e-05, "loss": 0.4758, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.49304168092865785, "learning_rate": 3.7785339305300916e-05, "loss": 0.4984, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5598110545825408, "learning_rate": 3.7759400935650025e-05, "loss": 0.5024, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5558441736980955, "learning_rate": 3.77333205623025e-05, "loss": 0.4774, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.5786874840191397, "learning_rate": 3.7707098393796295e-05, "loss": 0.5087, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5463939324795478, "learning_rate": 3.7680734639803185e-05, "loss": 0.4859, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5191168838685075, "learning_rate": 3.765422951112704e-05, "loss": 0.4932, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.5101146198831765, "learning_rate": 3.762758321970216e-05, "loss": 0.474, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.528864873806103, "learning_rate": 3.7600795978591584e-05, "loss": 0.4942, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5866419629772458, "learning_rate": 3.757386800198538e-05, "loss": 0.5086, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.5971872998638541, "learning_rate": 3.7546799505198925e-05, "loss": 0.4887, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5642889644042073, "learning_rate": 3.7519590704671197e-05, "loss": 0.4999, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5693990406331871, "learning_rate": 3.749224181796305e-05, "loss": 0.4979, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5740431527679462, "learning_rate": 3.746475306375545e-05, "loss": 0.4921, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.558999134908294, "learning_rate": 3.743712466184774e-05, "loss": 0.4996, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.5730451308726202, "learning_rate": 3.7409356833155885e-05, "loss": 0.491, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.5448185733044457, "learning_rate": 3.73814497997107e-05, "loss": 0.5064, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.5759801513039562, "learning_rate": 3.7353403784656095e-05, "loss": 0.4891, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5276179812388672, "learning_rate": 3.732521901224724e-05, "loss": 0.4916, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.5308111394350478, "learning_rate": 3.7296895707848844e-05, "loss": 0.4906, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.5296932208923681, "learning_rate": 3.7268434097933275e-05, "loss": 0.4904, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.5270400416803604, "learning_rate": 3.723983441007882e-05, "loss": 0.478, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5699562777333814, "learning_rate": 3.721109687296781e-05, "loss": 0.4931, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.5552170532527954, "learning_rate": 3.718222171638484e-05, "loss": 0.4714, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5402872944495489, "learning_rate": 3.715320917121488e-05, "loss": 0.4731, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.551857791205388, "learning_rate": 3.712405946944149e-05, "loss": 0.5099, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.49715019618804757, "learning_rate": 3.709477284414488e-05, "loss": 0.4751, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.49053872343250554, "learning_rate": 3.7065349529500136e-05, "loss": 0.4961, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.508721222806956, "learning_rate": 3.7035789760775305e-05, "loss": 0.4787, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.5418461134690683, "learning_rate": 3.70060937743295e-05, "loss": 0.5058, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.5456474975941373, "learning_rate": 3.6976261807611045e-05, "loss": 0.5034, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.5106251321497345, "learning_rate": 3.694629409915555e-05, "loss": 0.485, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.5755618036992272, "learning_rate": 3.691619088858401e-05, "loss": 0.4953, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5749161979609015, "learning_rate": 3.68859524166009e-05, "loss": 0.4821, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.4844837331656507, "learning_rate": 3.6855578924992226e-05, "loss": 0.4798, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.6051820803307696, "learning_rate": 3.6825070656623626e-05, "loss": 0.4978, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.47653998778038426, "learning_rate": 3.67944278554384e-05, "loss": 0.4743, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.5297019070025802, "learning_rate": 3.676365076645557e-05, "loss": 0.4984, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.46316015031714736, "learning_rate": 3.673273963576791e-05, "loss": 0.4871, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.5351008615057128, "learning_rate": 3.670169471054001e-05, "loss": 0.48, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.5471868490715748, "learning_rate": 3.6670516239006254e-05, "loss": 0.4901, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.5243171789614448, "learning_rate": 3.663920447046888e-05, "loss": 0.4928, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.5362515340462563, "learning_rate": 3.6607759655295954e-05, "loss": 0.4918, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.6064573263169678, "learning_rate": 3.657618204491937e-05, "loss": 0.4805, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.548920554978188, "learning_rate": 3.6544471891832875e-05, "loss": 0.5018, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.5917990538325143, "learning_rate": 3.6512629449589983e-05, "loss": 0.4698, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.4781950017087611, "learning_rate": 3.6480654972802045e-05, "loss": 0.4866, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5983279669201681, "learning_rate": 3.644854871713611e-05, "loss": 0.502, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.5320904858470831, "learning_rate": 3.6416310939312924e-05, "loss": 0.4657, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.6285246735132971, "learning_rate": 3.638394189710493e-05, "loss": 0.4726, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.5821966262506304, "learning_rate": 3.635144184933412e-05, "loss": 0.4686, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.5876291629118582, "learning_rate": 3.6318811055869994e-05, "loss": 0.4968, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.5870116826119453, "learning_rate": 3.628604977762752e-05, "loss": 0.4697, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.47492725256680673, "learning_rate": 3.6253158276565004e-05, "loss": 0.4953, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5100247229172287, "learning_rate": 3.6220136815682016e-05, "loss": 0.4819, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.47181352219471256, "learning_rate": 3.618698565901727e-05, "loss": 0.502, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.5707086378101582, "learning_rate": 3.615370507164654e-05, "loss": 0.4758, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.4788517802914072, "learning_rate": 3.61202953196805e-05, "loss": 0.488, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5373107460086869, "learning_rate": 3.6086756670262654e-05, "loss": 0.4804, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.641788923204004, "learning_rate": 3.6053089391567135e-05, "loss": 0.4979, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.49437306753052157, "learning_rate": 3.601929375279662e-05, "loss": 0.4965, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.5621034583374936, "learning_rate": 3.598537002418012e-05, "loss": 0.4836, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.5495984838707033, "learning_rate": 3.5951318476970885e-05, "loss": 0.4686, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5653564667018579, "learning_rate": 3.591713938344416e-05, "loss": 0.4927, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.554422017863361, "learning_rate": 3.588283301689507e-05, "loss": 0.4876, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.5615467346267387, "learning_rate": 3.5848399651636424e-05, "loss": 0.4792, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.4880062362533424, "learning_rate": 3.5813839562996473e-05, "loss": 0.4773, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5665102817101891, "learning_rate": 3.5779153027316775e-05, "loss": 0.4963, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.46545563246540683, "learning_rate": 3.574434032194994e-05, "loss": 0.5161, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.5757428911583329, "learning_rate": 3.5709401725257436e-05, "loss": 0.4873, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4437197056766766, "learning_rate": 3.5674337516607346e-05, "loss": 0.4819, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5461372596142765, "learning_rate": 3.563914797637216e-05, "loss": 0.4742, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.45508846031079775, "learning_rate": 3.560383338592649e-05, "loss": 0.4814, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5690891225135918, "learning_rate": 3.556839402764487e-05, "loss": 0.4922, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.5278158616903371, "learning_rate": 3.553283018489946e-05, "loss": 0.4975, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.49130064350331715, "learning_rate": 3.54971421420578e-05, "loss": 0.4721, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5361443912056449, "learning_rate": 3.5461330184480524e-05, "loss": 0.476, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.48196773268715115, "learning_rate": 3.54253945985191e-05, "loss": 0.4701, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.5331981417514993, "learning_rate": 3.5389335671513524e-05, "loss": 0.4796, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.5378734600623047, "learning_rate": 3.5353153691789986e-05, "loss": 0.4818, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.6582774504571565, "learning_rate": 3.531684894865866e-05, "loss": 0.5121, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5164964993085032, "learning_rate": 3.528042173241128e-05, "loss": 0.5014, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.6882169568659722, "learning_rate": 3.524387233431892e-05, "loss": 0.483, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.4744234050986169, "learning_rate": 3.520720104662958e-05, "loss": 0.5, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.6009027608730049, "learning_rate": 3.5170408162565904e-05, "loss": 0.4817, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.5287187857921505, "learning_rate": 3.513349397632281e-05, "loss": 0.4849, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4828564323219592, "learning_rate": 3.5096458783065145e-05, "loss": 0.484, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5699493426262903, "learning_rate": 3.505930287892533e-05, "loss": 0.4977, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.5092291987812486, "learning_rate": 3.502202656100099e-05, "loss": 0.4958, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5524686333924278, "learning_rate": 3.498463012735256e-05, "loss": 0.5087, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.4874222100629681, "learning_rate": 3.494711387700094e-05, "loss": 0.477, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.5001925397016953, "learning_rate": 3.490947810992505e-05, "loss": 0.4772, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.5400355602406566, "learning_rate": 3.48717231270595e-05, "loss": 0.4866, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.47767029283085327, "learning_rate": 3.483384923029211e-05, "loss": 0.4812, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.5479350916147171, "learning_rate": 3.479585672246156e-05, "loss": 0.4934, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.5899855907053992, "learning_rate": 3.4757745907354924e-05, "loss": 0.5083, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4363297169763939, "learning_rate": 3.471951708970527e-05, "loss": 0.4855, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.5812368067529207, "learning_rate": 3.468117057518921e-05, "loss": 0.496, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.5015129673488798, "learning_rate": 3.4642706670424426e-05, "loss": 0.4947, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.5116474514097498, "learning_rate": 3.460412568296731e-05, "loss": 0.4897, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.5170998992205741, "learning_rate": 3.456542792131039e-05, "loss": 0.4769, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.46644734262568927, "learning_rate": 3.4526613694879936e-05, "loss": 0.4891, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.5358489676388226, "learning_rate": 3.448768331403348e-05, "loss": 0.4988, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.47886588155928467, "learning_rate": 3.44486370900573e-05, "loss": 0.5071, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.5109264450145157, "learning_rate": 3.440947533516396e-05, "loss": 0.4763, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.4897587560697806, "learning_rate": 3.4370198362489816e-05, "loss": 0.4934, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.5719836708781268, "learning_rate": 3.43308064860925e-05, "loss": 0.484, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5040276980978949, "learning_rate": 3.4291300020948393e-05, "loss": 0.4738, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.5263423876253481, "learning_rate": 3.425167928295015e-05, "loss": 0.4832, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.5051441375809498, "learning_rate": 3.421194458890411e-05, "loss": 0.5025, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.5127520599183142, "learning_rate": 3.4172096256527865e-05, "loss": 0.5148, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5513621075040409, "learning_rate": 3.4132134604447595e-05, "loss": 0.5109, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.5024819441424663, "learning_rate": 3.409205995219561e-05, "loss": 0.4596, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.518707032372845, "learning_rate": 3.4051872620207765e-05, "loss": 0.5118, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.5156905321541366, "learning_rate": 3.40115729298209e-05, "loss": 0.5116, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.4867964714284974, "learning_rate": 3.397116120327025e-05, "loss": 0.484, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.6014996269740494, "learning_rate": 3.3930637763686916e-05, "loss": 0.4841, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.4647727819493652, "learning_rate": 3.389000293509524e-05, "loss": 0.4873, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.547824499899747, "learning_rate": 3.3849257042410225e-05, "loss": 0.4697, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5260125185716793, "learning_rate": 3.380840041143494e-05, "loss": 0.4944, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.5600930183951934, "learning_rate": 3.376743336885792e-05, "loss": 0.5147, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.5076689334422966, "learning_rate": 3.372635624225055e-05, "loss": 0.4746, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.5417905070697691, "learning_rate": 3.3685169360064445e-05, "loss": 0.4803, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.5783553470519563, "learning_rate": 3.3643873051628804e-05, "loss": 0.4907, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4649515783335907, "learning_rate": 3.3602467647147814e-05, "loss": 0.4955, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.5540812953415463, "learning_rate": 3.356095347769799e-05, "loss": 0.4796, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.5692337860924273, "learning_rate": 3.351933087522552e-05, "loss": 0.4903, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.4469460890627283, "learning_rate": 3.3477600172543626e-05, "loss": 0.4653, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.5900474900018782, "learning_rate": 3.3435761703329894e-05, "loss": 0.4903, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.5087401555722508, "learning_rate": 3.3393815802123606e-05, "loss": 0.4577, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.5074254797398656, "learning_rate": 3.335176280432308e-05, "loss": 0.501, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.523849468226602, "learning_rate": 3.330960304618295e-05, "loss": 0.4848, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4758506385068162, "learning_rate": 3.326733686481153e-05, "loss": 0.4818, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.5750243706820993, "learning_rate": 3.3224964598168084e-05, "loss": 0.4891, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.4952417721394734, "learning_rate": 3.318248658506012e-05, "loss": 0.5048, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.5798902737395256, "learning_rate": 3.313990316514069e-05, "loss": 0.4709, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.4489233963572887, "learning_rate": 3.309721467890571e-05, "loss": 0.4724, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.5546316104722233, "learning_rate": 3.305442146769115e-05, "loss": 0.4991, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.46436026472355896, "learning_rate": 3.30115238736704e-05, "loss": 0.4793, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.5739058032114812, "learning_rate": 3.296852223985148e-05, "loss": 0.4876, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4652110121108562, "learning_rate": 3.2925416910074315e-05, "loss": 0.4698, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.5662376894024369, "learning_rate": 3.288220822900796e-05, "loss": 0.5026, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.4712174989301672, "learning_rate": 3.283889654214788e-05, "loss": 0.4739, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.5299285947354505, "learning_rate": 3.279548219581317e-05, "loss": 0.4747, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.4526542924536292, "learning_rate": 3.275196553714379e-05, "loss": 0.4769, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.46000411472824815, "learning_rate": 3.270834691409778e-05, "loss": 0.4768, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.44157763511889775, "learning_rate": 3.266462667544849e-05, "loss": 0.4693, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.4949083013146015, "learning_rate": 3.262080517078178e-05, "loss": 0.4831, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.4294560409017387, "learning_rate": 3.257688275049323e-05, "loss": 0.4839, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.46180933494323106, "learning_rate": 3.253285976578535e-05, "loss": 0.4808, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.45243728201942823, "learning_rate": 3.2488736568664756e-05, "loss": 0.4826, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.51351205619077, "learning_rate": 3.244451351193935e-05, "loss": 0.4662, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.46584768254530323, "learning_rate": 3.240019094921551e-05, "loss": 0.485, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.6042580155796462, "learning_rate": 3.235576923489527e-05, "loss": 0.4649, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.46028364315252907, "learning_rate": 3.2311248724173476e-05, "loss": 0.4953, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5353309165137493, "learning_rate": 3.226662977303494e-05, "loss": 0.4866, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4576293627482752, "learning_rate": 3.2221912738251626e-05, "loss": 0.4868, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.5333704464158432, "learning_rate": 3.2177097977379736e-05, "loss": 0.4782, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.48232837521832095, "learning_rate": 3.21321858487569e-05, "loss": 0.4679, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.5343086309519128, "learning_rate": 3.208717671149931e-05, "loss": 0.4622, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.5084846943341056, "learning_rate": 3.204207092549882e-05, "loss": 0.4812, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.548877506745568, "learning_rate": 3.19968688514201e-05, "loss": 0.4685, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.5045707739572318, "learning_rate": 3.195157085069774e-05, "loss": 0.493, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.46329431991084774, "learning_rate": 3.190617728553332e-05, "loss": 0.483, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.526305032458585, "learning_rate": 3.1860688518892606e-05, "loss": 0.4797, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4522801518783839, "learning_rate": 3.181510491450254e-05, "loss": 0.4944, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.4701430240121163, "learning_rate": 3.176942683684842e-05, "loss": 0.4948, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.4933195129160558, "learning_rate": 3.1723654651170934e-05, "loss": 0.4778, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4467595185285928, "learning_rate": 3.167778872346327e-05, "loss": 0.4713, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.46322361221264335, "learning_rate": 3.163182942046815e-05, "loss": 0.4797, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.44961087708504865, "learning_rate": 3.158577710967494e-05, "loss": 0.4752, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.4774054094686284, "learning_rate": 3.153963215931669e-05, "loss": 0.4647, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.49149485710573126, "learning_rate": 3.14933949383672e-05, "loss": 0.4749, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.48684033835570584, "learning_rate": 3.144706581653805e-05, "loss": 0.4876, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.4856916025182546, "learning_rate": 3.140064516427566e-05, "loss": 0.4742, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.4547150925904022, "learning_rate": 3.135413335275833e-05, "loss": 0.4956, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.4939314506599313, "learning_rate": 3.130753075389327e-05, "loss": 0.4792, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.48371633928263574, "learning_rate": 3.1260837740313625e-05, "loss": 0.5038, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.43643749359885264, "learning_rate": 3.121405468537547e-05, "loss": 0.469, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.5166989197951006, "learning_rate": 3.116718196315488e-05, "loss": 0.4649, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.46203427957923665, "learning_rate": 3.1120219948444894e-05, "loss": 0.4827, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.5300668133246698, "learning_rate": 3.107316901675252e-05, "loss": 0.4857, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.5178875749641937, "learning_rate": 3.1026029544295745e-05, "loss": 0.4758, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.4692874472489337, "learning_rate": 3.097880190800057e-05, "loss": 0.4839, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.5506988203063027, "learning_rate": 3.093148648549788e-05, "loss": 0.4728, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4765317887170987, "learning_rate": 3.088408365512055e-05, "loss": 0.4741, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.5065926712494159, "learning_rate": 3.083659379590034e-05, "loss": 0.5012, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.4500378614487977, "learning_rate": 3.0789017287564913e-05, "loss": 0.4583, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.4698698511581421, "learning_rate": 3.074135451053475e-05, "loss": 0.4686, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.45970908829111534, "learning_rate": 3.069360584592015e-05, "loss": 0.4658, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.4746275930450633, "learning_rate": 3.064577167551816e-05, "loss": 0.4887, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.49581594543843027, "learning_rate": 3.059785238180953e-05, "loss": 0.4866, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.42633544523348305, "learning_rate": 3.054984834795566e-05, "loss": 0.468, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.46264229487461545, "learning_rate": 3.0501759957795537e-05, "loss": 0.4854, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.4794634878029046, "learning_rate": 3.0453587595842627e-05, "loss": 0.4738, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4487150563885244, "learning_rate": 3.0405331647281856e-05, "loss": 0.4867, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.46731104994296685, "learning_rate": 3.0356992497966508e-05, "loss": 0.4757, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.4327419172423697, "learning_rate": 3.0308570534415137e-05, "loss": 0.4667, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.46444772969874837, "learning_rate": 3.0260066143808467e-05, "loss": 0.491, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.43314091137361815, "learning_rate": 3.021147971398632e-05, "loss": 0.4961, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.4602974448596212, "learning_rate": 3.0162811633444478e-05, "loss": 0.461, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.478619212149016, "learning_rate": 3.0114062291331635e-05, "loss": 0.4797, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.48390991774742276, "learning_rate": 3.0065232077446217e-05, "loss": 0.4667, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.43329276420670887, "learning_rate": 3.001632138223332e-05, "loss": 0.4815, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.8339339423108193, "learning_rate": 2.9967330596781565e-05, "loss": 0.325, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.4691129239787076, "learning_rate": 2.9918260112819952e-05, "loss": 0.3473, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 1.1366582353921189, "learning_rate": 2.9869110322714778e-05, "loss": 0.321, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5578842841922895, "learning_rate": 2.9819881619466447e-05, "loss": 0.3218, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.5619557829416396, "learning_rate": 2.9770574396706364e-05, "loss": 0.3234, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5128717877648574, "learning_rate": 2.972118904869376e-05, "loss": 0.3271, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.5277101622538808, "learning_rate": 2.9671725970312563e-05, "loss": 0.3349, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.47953462677702086, "learning_rate": 2.9622185557068238e-05, "loss": 0.3346, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.5113751095312188, "learning_rate": 2.95725682050846e-05, "loss": 0.3327, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.5000721472705518, "learning_rate": 2.9522874311100684e-05, "loss": 0.3205, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.49757587660592295, "learning_rate": 2.9473104272467526e-05, "loss": 0.3514, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4739407558909954, "learning_rate": 2.942325848714505e-05, "loss": 0.3373, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.5774455213926731, "learning_rate": 2.9373337353698804e-05, "loss": 0.3242, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4344061867005027, "learning_rate": 2.932334127129686e-05, "loss": 0.3331, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.6097665871578132, "learning_rate": 2.9273270639706547e-05, "loss": 0.3292, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.4552449150420313, "learning_rate": 2.922312585929131e-05, "loss": 0.332, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.6219797515838164, "learning_rate": 2.9172907331007478e-05, "loss": 0.3436, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.4728919009476746, "learning_rate": 2.9122615456401053e-05, "loss": 0.362, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.5281815942738617, "learning_rate": 2.9072250637604535e-05, "loss": 0.32, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.5128283816656111, "learning_rate": 2.9021813277333667e-05, "loss": 0.339, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.45257816760521163, "learning_rate": 2.8971303778884244e-05, "loss": 0.3192, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.4492496007770091, "learning_rate": 2.8920722546128863e-05, "loss": 0.3151, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.5121144406738912, "learning_rate": 2.887006998351372e-05, "loss": 0.3412, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4540440147590678, "learning_rate": 2.881934649605535e-05, "loss": 0.3329, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.4521610394315523, "learning_rate": 2.8768552489337408e-05, "loss": 0.3142, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.4286512964933327, "learning_rate": 2.8717688369507425e-05, "loss": 0.3166, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.4725441675363283, "learning_rate": 2.8666754543273535e-05, "loss": 0.3178, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4527610523612125, "learning_rate": 2.8615751417901273e-05, "loss": 0.3169, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.45007832290459987, "learning_rate": 2.856467940121025e-05, "loss": 0.3159, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.4818653975759704, "learning_rate": 2.8513538901570964e-05, "loss": 0.334, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.43802447656655213, "learning_rate": 2.846233032790149e-05, "loss": 0.3071, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.44301373400373334, "learning_rate": 2.84110540896642e-05, "loss": 0.3344, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.42784607703604594, "learning_rate": 2.8359710596862555e-05, "loss": 0.3377, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.40374966180628213, "learning_rate": 2.8308300260037734e-05, "loss": 0.3187, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3879705174828896, "learning_rate": 2.8256823490265424e-05, "loss": 0.3337, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.39654282764999044, "learning_rate": 2.8205280699152515e-05, "loss": 0.3367, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.408653947726844, "learning_rate": 2.8153672298833777e-05, "loss": 0.3325, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.43578888677175887, "learning_rate": 2.8101998701968615e-05, "loss": 0.3151, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.4113670020057572, "learning_rate": 2.805026032173773e-05, "loss": 0.3222, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.43702513455252445, "learning_rate": 2.7998457571839832e-05, "loss": 0.3059, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.43642145362665885, "learning_rate": 2.7946590866488322e-05, "loss": 0.3283, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.44241936659693337, "learning_rate": 2.7894660620408e-05, "loss": 0.3137, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.41837902318516995, "learning_rate": 2.784266724883173e-05, "loss": 0.3274, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.4666424943833771, "learning_rate": 2.7790611167497128e-05, "loss": 0.351, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.44571533280400666, "learning_rate": 2.7738492792643224e-05, "loss": 0.3242, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.4211854390394392, "learning_rate": 2.768631254100716e-05, "loss": 0.3284, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.43544351352949384, "learning_rate": 2.7634070829820836e-05, "loss": 0.3289, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.446435376866576, "learning_rate": 2.7581768076807592e-05, "loss": 0.3239, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.44882930706841856, "learning_rate": 2.7529404700178832e-05, "loss": 0.3229, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.46287944384290924, "learning_rate": 2.7476981118630735e-05, "loss": 0.3483, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.47440072366161173, "learning_rate": 2.742449775134085e-05, "loss": 0.3464, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.4376499224814036, "learning_rate": 2.7371955017964788e-05, "loss": 0.3169, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.4837497196661638, "learning_rate": 2.7319353338632845e-05, "loss": 0.3301, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.45148757774619186, "learning_rate": 2.7266693133946645e-05, "loss": 0.3464, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.48147382478623024, "learning_rate": 2.7213974824975785e-05, "loss": 0.3147, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.47743355145315, "learning_rate": 2.7161198833254464e-05, "loss": 0.341, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.4751520058970019, "learning_rate": 2.7108365580778095e-05, "loss": 0.3517, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.43777620648561755, "learning_rate": 2.705547548999996e-05, "loss": 0.351, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.4243026044769321, "learning_rate": 2.7002528983827817e-05, "loss": 0.3411, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.45976186019761484, "learning_rate": 2.6949526485620517e-05, "loss": 0.3453, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.4578714624213736, "learning_rate": 2.6896468419184623e-05, "loss": 0.3588, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.471956144490132, "learning_rate": 2.6843355208771024e-05, "loss": 0.3405, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.4439380727486395, "learning_rate": 2.6790187279071536e-05, "loss": 0.3233, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4402877272312737, "learning_rate": 2.67369650552155e-05, "loss": 0.3267, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.44298519987696583, "learning_rate": 2.6683688962766407e-05, "loss": 0.3334, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.434380655881324, "learning_rate": 2.6630359427718468e-05, "loss": 0.3365, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.4394038584701094, "learning_rate": 2.6576976876493225e-05, "loss": 0.3323, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.4280387131374094, "learning_rate": 2.652354173593614e-05, "loss": 0.3284, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.4605871140267334, "learning_rate": 2.647005443331317e-05, "loss": 0.3269, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.4405771604473804, "learning_rate": 2.6416515396307354e-05, "loss": 0.3592, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.43736029155670025, "learning_rate": 2.636292505301542e-05, "loss": 0.3312, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.4270924036495241, "learning_rate": 2.630928383194431e-05, "loss": 0.335, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.4142172400596887, "learning_rate": 2.625559216200781e-05, "loss": 0.3347, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.45625396935478574, "learning_rate": 2.620185047252308e-05, "loss": 0.334, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.40776983928187926, "learning_rate": 2.614805919320723e-05, "loss": 0.3325, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.4034038141913908, "learning_rate": 2.6094218754173895e-05, "loss": 0.3305, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.45058626001192215, "learning_rate": 2.60403295859298e-05, "loss": 0.3234, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.4161733892931453, "learning_rate": 2.5986392119371297e-05, "loss": 0.3398, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.4066704850291176, "learning_rate": 2.5932406785780928e-05, "loss": 0.3309, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.4017370765381484, "learning_rate": 2.5878374016823987e-05, "loss": 0.3513, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.39481955393922014, "learning_rate": 2.5824294244545045e-05, "loss": 0.3175, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.47297788989320966, "learning_rate": 2.577016790136453e-05, "loss": 0.3429, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.42490989487296804, "learning_rate": 2.5715995420075225e-05, "loss": 0.3427, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.4612985025993304, "learning_rate": 2.5661777233838864e-05, "loss": 0.3258, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.39756380391550317, "learning_rate": 2.5607513776182616e-05, "loss": 0.3245, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.42473708022214673, "learning_rate": 2.5553205480995633e-05, "loss": 0.3346, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.4854478847778097, "learning_rate": 2.5498852782525604e-05, "loss": 0.3286, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.4133716896936167, "learning_rate": 2.5444456115375252e-05, "loss": 0.3347, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.4407966207091612, "learning_rate": 2.539001591449889e-05, "loss": 0.3308, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.46697705974603043, "learning_rate": 2.53355326151989e-05, "loss": 0.3292, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.45628514543931586, "learning_rate": 2.5281006653122288e-05, "loss": 0.3369, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.4469125725711548, "learning_rate": 2.5226438464257217e-05, "loss": 0.336, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.4945191336121824, "learning_rate": 2.5171828484929447e-05, "loss": 0.3259, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3925062980053037, "learning_rate": 2.5117177151798934e-05, "loss": 0.3381, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.4804549749522376, "learning_rate": 2.506248490185627e-05, "loss": 0.3409, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 2.5982644769750625, "learning_rate": 2.500775217241923e-05, "loss": 0.319, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.5239052815183138, "learning_rate": 2.4952979401129266e-05, "loss": 0.3321, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.42435701341487825, "learning_rate": 2.4898167025948e-05, "loss": 0.3142, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.4950340053750679, "learning_rate": 2.4843315485153703e-05, "loss": 0.3365, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.43866209711693177, "learning_rate": 2.4788425217337856e-05, "loss": 0.3399, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.4665364596082204, "learning_rate": 2.4733496661401572e-05, "loss": 0.3409, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.42264290319972614, "learning_rate": 2.4678530256552114e-05, "loss": 0.3419, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.44727948872275425, "learning_rate": 2.46235264422994e-05, "loss": 0.3391, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.4502511828830713, "learning_rate": 2.4568485658452452e-05, "loss": 0.3396, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.5194733346226841, "learning_rate": 2.451340834511592e-05, "loss": 0.331, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.42430122318074776, "learning_rate": 2.4458294942686528e-05, "loss": 0.3034, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.5520366618993449, "learning_rate": 2.440314589184958e-05, "loss": 0.3226, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.4324824049493801, "learning_rate": 2.434796163357541e-05, "loss": 0.3447, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.4908482804468066, "learning_rate": 2.429274260911588e-05, "loss": 0.3305, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.42513166221129983, "learning_rate": 2.423748926000084e-05, "loss": 0.3422, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.4945894553055499, "learning_rate": 2.418220202803459e-05, "loss": 0.3386, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.4236554677332678, "learning_rate": 2.412688135529237e-05, "loss": 0.3452, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.4669799884080887, "learning_rate": 2.4071527684116807e-05, "loss": 0.3469, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.4421122910598963, "learning_rate": 2.4016141457114372e-05, "loss": 0.3392, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.5002755295995168, "learning_rate": 2.396072311715187e-05, "loss": 0.3374, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.4747581987861562, "learning_rate": 2.3905273107352863e-05, "loss": 0.3512, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.40676395826223527, "learning_rate": 2.3849791871094157e-05, "loss": 0.324, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.47294943197381534, "learning_rate": 2.379427985200223e-05, "loss": 0.3236, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.4668352381355211, "learning_rate": 2.373873749394972e-05, "loss": 0.3401, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.4130504244794218, "learning_rate": 2.3683165241051836e-05, "loss": 0.345, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.4487997970525513, "learning_rate": 2.3627563537662823e-05, "loss": 0.3292, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.41949545370819286, "learning_rate": 2.3571932828372433e-05, "loss": 0.3366, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.4277892671784573, "learning_rate": 2.351627355800233e-05, "loss": 0.3444, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.44909139528815767, "learning_rate": 2.346058617160256e-05, "loss": 0.2964, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.4100286762423897, "learning_rate": 2.3404871114447976e-05, "loss": 0.3265, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.4593230817216869, "learning_rate": 2.334912883203469e-05, "loss": 0.3367, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.385452675480763, "learning_rate": 2.3293359770076505e-05, "loss": 0.3508, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.4735092145876606, "learning_rate": 2.323756437450136e-05, "loss": 0.311, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.41351890814797143, "learning_rate": 2.3181743091447754e-05, "loss": 0.3197, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.41059858262911053, "learning_rate": 2.3125896367261164e-05, "loss": 0.3362, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.3926051731611716, "learning_rate": 2.307002464849052e-05, "loss": 0.3419, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.41589138397587355, "learning_rate": 2.30141283818846e-05, "loss": 0.3418, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.40344040174521884, "learning_rate": 2.2958208014388462e-05, "loss": 0.329, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3980818215480711, "learning_rate": 2.2902263993139857e-05, "loss": 0.3344, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.4295235771635097, "learning_rate": 2.2846296765465708e-05, "loss": 0.335, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.40355833906002414, "learning_rate": 2.2790306778878465e-05, "loss": 0.3164, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.4026028778597257, "learning_rate": 2.273429448107257e-05, "loss": 0.31, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3902905642858299, "learning_rate": 2.2678260319920868e-05, "loss": 0.3273, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.3996391426847114, "learning_rate": 2.262220474347102e-05, "loss": 0.3303, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.45715216551853494, "learning_rate": 2.2566128199941918e-05, "loss": 0.3322, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.4284736024650663, "learning_rate": 2.2510031137720104e-05, "loss": 0.3303, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.40295098476750496, "learning_rate": 2.2453914005356206e-05, "loss": 0.3358, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.44000389814130464, "learning_rate": 2.2397777251561302e-05, "loss": 0.317, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.40207852957197887, "learning_rate": 2.2341621325203393e-05, "loss": 0.3475, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.4139741734466213, "learning_rate": 2.2285446675303764e-05, "loss": 0.3509, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.4091575006407791, "learning_rate": 2.2229253751033423e-05, "loss": 0.3325, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.4065905320150205, "learning_rate": 2.2173043001709492e-05, "loss": 0.3354, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3963286816769848, "learning_rate": 2.2116814876791627e-05, "loss": 0.3285, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.3891851064478027, "learning_rate": 2.2060569825878413e-05, "loss": 0.338, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.4319199657585271, "learning_rate": 2.2004308298703777e-05, "loss": 0.3507, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.4206710908749575, "learning_rate": 2.1948030745133396e-05, "loss": 0.3136, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.41781157657671564, "learning_rate": 2.1891737615161083e-05, "loss": 0.3232, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.4272352500432106, "learning_rate": 2.1835429358905218e-05, "loss": 0.3416, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.41447755612280435, "learning_rate": 2.17791064266051e-05, "loss": 0.3352, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.43196487174023934, "learning_rate": 2.172276926861741e-05, "loss": 0.3464, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.39090712527980026, "learning_rate": 2.166641833541255e-05, "loss": 0.3272, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.4371016602870722, "learning_rate": 2.161005407757109e-05, "loss": 0.3268, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.41893031615206366, "learning_rate": 2.155367694578013e-05, "loss": 0.3453, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.400440073427443, "learning_rate": 2.1497287390829712e-05, "loss": 0.3218, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.42032722632854236, "learning_rate": 2.1440885863609208e-05, "loss": 0.342, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.4105424570312392, "learning_rate": 2.1384472815103737e-05, "loss": 0.3249, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.41344002740823377, "learning_rate": 2.1328048696390534e-05, "loss": 0.3168, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.3913827887278951, "learning_rate": 2.1271613958635342e-05, "loss": 0.3366, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.40248451777937383, "learning_rate": 2.1215169053088825e-05, "loss": 0.3097, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.395121194285474, "learning_rate": 2.1158714431082937e-05, "loss": 0.3532, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.41571150171908267, "learning_rate": 2.110225054402733e-05, "loss": 0.3329, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.41350075457275076, "learning_rate": 2.1045777843405747e-05, "loss": 0.3197, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.40467338097050953, "learning_rate": 2.09892967807724e-05, "loss": 0.3156, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.41509521667926963, "learning_rate": 2.093280780774835e-05, "loss": 0.3381, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.383853289397417, "learning_rate": 2.087631137601793e-05, "loss": 0.3323, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.4526757503888725, "learning_rate": 2.0819807937325104e-05, "loss": 0.3357, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.39336483406177086, "learning_rate": 2.0763297943469847e-05, "loss": 0.3417, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.38262764100039437, "learning_rate": 2.070678184630458e-05, "loss": 0.3436, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.43124197601252745, "learning_rate": 2.06502600977305e-05, "loss": 0.3371, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3968748474225111, "learning_rate": 2.0593733149694008e-05, "loss": 0.3483, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3905745793919788, "learning_rate": 2.0537201454183074e-05, "loss": 0.3449, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.38334868407333006, "learning_rate": 2.0480665463223626e-05, "loss": 0.3387, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.4271407283781704, "learning_rate": 2.042412562887594e-05, "loss": 0.3279, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.40210345507729356, "learning_rate": 2.0367582403231033e-05, "loss": 0.347, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.39818812463912956, "learning_rate": 2.0311036238407023e-05, "loss": 0.344, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.415815643907474, "learning_rate": 2.0254487586545534e-05, "loss": 0.3446, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.4042959175888891, "learning_rate": 2.0197936899808088e-05, "loss": 0.3393, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.42318319143147237, "learning_rate": 2.0141384630372466e-05, "loss": 0.3296, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.38141796954556834, "learning_rate": 2.0084831230429106e-05, "loss": 0.3524, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.39620319044350544, "learning_rate": 2.0028277152177492e-05, "loss": 0.3173, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3886730452521282, "learning_rate": 1.9971722847822518e-05, "loss": 0.3354, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3933852726342255, "learning_rate": 1.99151687695709e-05, "loss": 0.3288, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.3846123328056909, "learning_rate": 1.9858615369627537e-05, "loss": 0.3317, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.3996152898473763, "learning_rate": 1.9802063100191916e-05, "loss": 0.3257, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.4231791027090248, "learning_rate": 1.974551241345447e-05, "loss": 0.3469, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.384124651374625, "learning_rate": 1.9688963761592984e-05, "loss": 0.3219, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.41307054730699105, "learning_rate": 1.963241759676897e-05, "loss": 0.3407, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.41186952790359727, "learning_rate": 1.9575874371124066e-05, "loss": 0.314, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.40400640457009757, "learning_rate": 1.951933453677638e-05, "loss": 0.3364, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.3868757392219315, "learning_rate": 1.9462798545816932e-05, "loss": 0.347, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.3983426371426568, "learning_rate": 1.9406266850305996e-05, "loss": 0.3172, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.42032461283156924, "learning_rate": 1.9349739902269503e-05, "loss": 0.3299, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3777716957973299, "learning_rate": 1.9293218153695425e-05, "loss": 0.3249, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.41144367472879806, "learning_rate": 1.9236702056530153e-05, "loss": 0.3252, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.39338926214699554, "learning_rate": 1.9180192062674907e-05, "loss": 0.3225, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.40909447271748256, "learning_rate": 1.9123688623982076e-05, "loss": 0.3422, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.42036257695286333, "learning_rate": 1.906719219225165e-05, "loss": 0.3217, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.41785987049871687, "learning_rate": 1.9010703219227603e-05, "loss": 0.3162, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.4212122376070445, "learning_rate": 1.8954222156594256e-05, "loss": 0.372, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.45659712702248456, "learning_rate": 1.8897749455972673e-05, "loss": 0.3543, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.45784285301738065, "learning_rate": 1.884128556891707e-05, "loss": 0.3337, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.4056352034812265, "learning_rate": 1.878483094691119e-05, "loss": 0.3226, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.42404889470277995, "learning_rate": 1.8728386041364664e-05, "loss": 0.3425, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.4367029278611294, "learning_rate": 1.867195130360947e-05, "loss": 0.3231, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.386005220374516, "learning_rate": 1.8615527184896263e-05, "loss": 0.3395, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.40265399881742625, "learning_rate": 1.8559114136390795e-05, "loss": 0.3437, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.43713581591636763, "learning_rate": 1.8502712609170298e-05, "loss": 0.3256, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.40028468336818324, "learning_rate": 1.8446323054219876e-05, "loss": 0.339, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.3990576734741206, "learning_rate": 1.838994592242891e-05, "loss": 0.3389, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.4210731960668102, "learning_rate": 1.8333581664587453e-05, "loss": 0.3135, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3829965823028002, "learning_rate": 1.8277230731382593e-05, "loss": 0.3227, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3899869437409957, "learning_rate": 1.82208935733949e-05, "loss": 0.3219, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.4024777461442741, "learning_rate": 1.8164570641094793e-05, "loss": 0.3418, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.4094345431617355, "learning_rate": 1.810826238483892e-05, "loss": 0.3156, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.3768765514954934, "learning_rate": 1.8051969254866608e-05, "loss": 0.3444, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.4147162045045112, "learning_rate": 1.7995691701296226e-05, "loss": 0.3358, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.4039138139703359, "learning_rate": 1.7939430174121593e-05, "loss": 0.3549, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.38130716577859886, "learning_rate": 1.788318512320838e-05, "loss": 0.3364, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3751496817813226, "learning_rate": 1.782695699829051e-05, "loss": 0.3305, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.4238068480209488, "learning_rate": 1.7770746248966587e-05, "loss": 0.3432, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.4196613790963719, "learning_rate": 1.7714553324696243e-05, "loss": 0.3409, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3949119427474114, "learning_rate": 1.7658378674796614e-05, "loss": 0.3286, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.42384249784864536, "learning_rate": 1.76022227484387e-05, "loss": 0.3421, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.3904396112883544, "learning_rate": 1.7546085994643807e-05, "loss": 0.3289, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.41106325284989287, "learning_rate": 1.7489968862279902e-05, "loss": 0.322, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3979265630355674, "learning_rate": 1.743387180005809e-05, "loss": 0.3462, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.4034072784950189, "learning_rate": 1.737779525652899e-05, "loss": 0.3402, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.3955836043378155, "learning_rate": 1.732173968007914e-05, "loss": 0.3339, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.39013273869153575, "learning_rate": 1.7265705518927437e-05, "loss": 0.3391, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.3882722516499822, "learning_rate": 1.7209693221121542e-05, "loss": 0.3297, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.3976914271794364, "learning_rate": 1.7153703234534302e-05, "loss": 0.3161, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.3976828339687105, "learning_rate": 1.709773600686015e-05, "loss": 0.3397, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.37709984507836336, "learning_rate": 1.7041791985611548e-05, "loss": 0.3274, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.3787738433251946, "learning_rate": 1.69858716181154e-05, "loss": 0.3344, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.3937971115023311, "learning_rate": 1.692997535150948e-05, "loss": 0.3419, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.3946794861897991, "learning_rate": 1.687410363273884e-05, "loss": 0.3218, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3936640999952649, "learning_rate": 1.6818256908552257e-05, "loss": 0.3287, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3984231286697707, "learning_rate": 1.6762435625498646e-05, "loss": 0.3408, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3882147317430609, "learning_rate": 1.67066402299235e-05, "loss": 0.3308, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.4110854130401826, "learning_rate": 1.6650871167965313e-05, "loss": 0.3384, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.40199775410729927, "learning_rate": 1.6595128885552028e-05, "loss": 0.3418, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.39631664063075106, "learning_rate": 1.653941382839745e-05, "loss": 0.3079, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.5844051715077655, "learning_rate": 1.6483726441997673e-05, "loss": 0.2406, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.40355424315862676, "learning_rate": 1.642806717162757e-05, "loss": 0.2315, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.43525267818489033, "learning_rate": 1.637243646233718e-05, "loss": 0.2187, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.67612199636371, "learning_rate": 1.6316834758948174e-05, "loss": 0.2346, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.48135318576200176, "learning_rate": 1.6261262506050282e-05, "loss": 0.2215, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.43377949257922366, "learning_rate": 1.620572014799777e-05, "loss": 0.2256, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.48757214687560724, "learning_rate": 1.6150208128905857e-05, "loss": 0.2221, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.4511246759785895, "learning_rate": 1.6094726892647147e-05, "loss": 0.214, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.3950552854271691, "learning_rate": 1.6039276882848135e-05, "loss": 0.2062, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.426108241972297, "learning_rate": 1.5983858542885635e-05, "loss": 0.2312, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.41553280491563493, "learning_rate": 1.5928472315883203e-05, "loss": 0.1955, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.4104900749797992, "learning_rate": 1.5873118644707633e-05, "loss": 0.1913, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.38107655556176695, "learning_rate": 1.5817797971965413e-05, "loss": 0.2246, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.37996720601464545, "learning_rate": 1.576251073999917e-05, "loss": 0.2233, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.37922548709962856, "learning_rate": 1.5707257390884126e-05, "loss": 0.2124, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.40559034873025984, "learning_rate": 1.5652038366424595e-05, "loss": 0.2083, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3901447582722214, "learning_rate": 1.5596854108150424e-05, "loss": 0.2154, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.34270193718368297, "learning_rate": 1.5541705057313476e-05, "loss": 0.2177, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3817166072910147, "learning_rate": 1.5486591654884086e-05, "loss": 0.2263, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3771145714225137, "learning_rate": 1.543151434154755e-05, "loss": 0.2161, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.34586124100987786, "learning_rate": 1.5376473557700615e-05, "loss": 0.2196, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3448929987347377, "learning_rate": 1.5321469743447893e-05, "loss": 0.2041, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.36176699225140563, "learning_rate": 1.5266503338598434e-05, "loss": 0.2179, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3524952143838226, "learning_rate": 1.5211574782662149e-05, "loss": 0.2306, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3494172927166949, "learning_rate": 1.5156684514846307e-05, "loss": 0.2081, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.350480967906485, "learning_rate": 1.5101832974052012e-05, "loss": 0.2032, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.36129737467727835, "learning_rate": 1.5047020598870737e-05, "loss": 0.2189, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.3465303378406385, "learning_rate": 1.4992247827580778e-05, "loss": 0.2055, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.36372850902809656, "learning_rate": 1.493751509814374e-05, "loss": 0.2231, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.34073346278180705, "learning_rate": 1.4882822848201073e-05, "loss": 0.2013, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.34537133727520153, "learning_rate": 1.4828171515070553e-05, "loss": 0.236, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3650657266252492, "learning_rate": 1.4773561535742793e-05, "loss": 0.2306, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.36395918712321323, "learning_rate": 1.4718993346877715e-05, "loss": 0.2375, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.3427933575259133, "learning_rate": 1.466446738480111e-05, "loss": 0.2299, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.35356752053238005, "learning_rate": 1.460998408550112e-05, "loss": 0.1997, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3544161107117949, "learning_rate": 1.4555543884624751e-05, "loss": 0.2155, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.35522421999720766, "learning_rate": 1.4501147217474402e-05, "loss": 0.2297, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.3382302827294267, "learning_rate": 1.444679451900437e-05, "loss": 0.1937, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.3466014692788482, "learning_rate": 1.4392486223817397e-05, "loss": 0.2192, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3396930097338801, "learning_rate": 1.4338222766161143e-05, "loss": 0.2104, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.3376735334910173, "learning_rate": 1.4284004579924777e-05, "loss": 0.1878, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.35332566605041343, "learning_rate": 1.4229832098635479e-05, "loss": 0.2283, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.33940502009913215, "learning_rate": 1.4175705755454963e-05, "loss": 0.2399, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.3473639498633109, "learning_rate": 1.412162598317602e-05, "loss": 0.2221, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.33175849691372, "learning_rate": 1.406759321421907e-05, "loss": 0.2236, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.33331319266533893, "learning_rate": 1.401360788062871e-05, "loss": 0.2164, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.3474144343926313, "learning_rate": 1.3959670414070204e-05, "loss": 0.1937, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.32856447182233084, "learning_rate": 1.3905781245826108e-05, "loss": 0.2179, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.33608976901999826, "learning_rate": 1.3851940806792778e-05, "loss": 0.2431, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3382653354269152, "learning_rate": 1.379814952747693e-05, "loss": 0.2193, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.3320819864017472, "learning_rate": 1.3744407837992193e-05, "loss": 0.2256, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.32656692352369976, "learning_rate": 1.3690716168055692e-05, "loss": 0.209, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.32794690170243057, "learning_rate": 1.363707494698459e-05, "loss": 0.2094, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.3340921295661278, "learning_rate": 1.358348460369265e-05, "loss": 0.1945, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.33068680241894094, "learning_rate": 1.352994556668684e-05, "loss": 0.2201, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3352796682684444, "learning_rate": 1.3476458264063865e-05, "loss": 0.2096, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.3503697180190396, "learning_rate": 1.342302312350678e-05, "loss": 0.2038, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3318440661905691, "learning_rate": 1.3369640572281537e-05, "loss": 0.2275, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.3487102094224883, "learning_rate": 1.3316311037233596e-05, "loss": 0.2108, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.34924424201696785, "learning_rate": 1.326303494478451e-05, "loss": 0.1954, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3345381331572745, "learning_rate": 1.3209812720928472e-05, "loss": 0.2166, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.32821537099551923, "learning_rate": 1.315664479122898e-05, "loss": 0.2265, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.34226388723671036, "learning_rate": 1.3103531580815378e-05, "loss": 0.2155, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.33155553547960914, "learning_rate": 1.3050473514379488e-05, "loss": 0.229, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.3379286940151672, "learning_rate": 1.2997471016172188e-05, "loss": 0.2173, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.3365558554639707, "learning_rate": 1.2944524510000042e-05, "loss": 0.2112, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.3402846402409037, "learning_rate": 1.2891634419221908e-05, "loss": 0.217, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.3297738463503754, "learning_rate": 1.2838801166745545e-05, "loss": 0.217, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.34673183141424546, "learning_rate": 1.2786025175024216e-05, "loss": 0.2148, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.3426253637848115, "learning_rate": 1.2733306866053357e-05, "loss": 0.1842, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.3239310705509952, "learning_rate": 1.2680646661367163e-05, "loss": 0.201, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.35169923515162527, "learning_rate": 1.2628044982035219e-05, "loss": 0.2137, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.35258940885405515, "learning_rate": 1.2575502248659155e-05, "loss": 0.2154, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.32527978935957375, "learning_rate": 1.2523018881369269e-05, "loss": 0.2159, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.3202125578042985, "learning_rate": 1.2470595299821176e-05, "loss": 0.2317, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.3362863781170653, "learning_rate": 1.2418231923192416e-05, "loss": 0.192, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.3333030744638227, "learning_rate": 1.2365929170179165e-05, "loss": 0.1971, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.32810982150940776, "learning_rate": 1.2313687458992848e-05, "loss": 0.2204, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.3454990207305584, "learning_rate": 1.2261507207356785e-05, "loss": 0.2066, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.32933454076111446, "learning_rate": 1.220938883250288e-05, "loss": 0.2109, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.3498908990587898, "learning_rate": 1.215733275116827e-05, "loss": 0.2048, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.33477026904798396, "learning_rate": 1.2105339379592005e-05, "loss": 0.2154, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.3390659699780498, "learning_rate": 1.2053409133511681e-05, "loss": 0.211, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.33440792326062857, "learning_rate": 1.2001542428160173e-05, "loss": 0.2143, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.34842356340356034, "learning_rate": 1.1949739678262278e-05, "loss": 0.2087, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.3280836891937239, "learning_rate": 1.189800129803139e-05, "loss": 0.2321, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3508129262224667, "learning_rate": 1.1846327701166228e-05, "loss": 0.2114, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.35611207884251483, "learning_rate": 1.1794719300847493e-05, "loss": 0.2209, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.32559691026799403, "learning_rate": 1.1743176509734582e-05, "loss": 0.2083, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.33116867447599124, "learning_rate": 1.1691699739962275e-05, "loss": 0.2221, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.3458545075734052, "learning_rate": 1.1640289403137456e-05, "loss": 0.2285, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.3349647239539823, "learning_rate": 1.1588945910335802e-05, "loss": 0.2182, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.32536408887942037, "learning_rate": 1.1537669672098517e-05, "loss": 0.2342, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.34108750113092623, "learning_rate": 1.1486461098429036e-05, "loss": 0.2214, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.3186117258049638, "learning_rate": 1.1435320598789747e-05, "loss": 0.239, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.3266931411236229, "learning_rate": 1.1384248582098736e-05, "loss": 0.2156, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.3321844877174524, "learning_rate": 1.1333245456726467e-05, "loss": 0.191, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.3348673590515222, "learning_rate": 1.128231163049258e-05, "loss": 0.1896, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.34274052673074473, "learning_rate": 1.123144751066259e-05, "loss": 0.2046, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.33102940851441603, "learning_rate": 1.1180653503944657e-05, "loss": 0.2139, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.3367345070213495, "learning_rate": 1.1129930016486287e-05, "loss": 0.2343, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.32787839370389166, "learning_rate": 1.107927745387114e-05, "loss": 0.2165, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.338581204763116, "learning_rate": 1.1028696221115766e-05, "loss": 0.2123, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.33851726056599474, "learning_rate": 1.0978186722666341e-05, "loss": 0.2022, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.327478890324158, "learning_rate": 1.0927749362395475e-05, "loss": 0.2082, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.3310387720948494, "learning_rate": 1.0877384543598954e-05, "loss": 0.228, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.3505266999148936, "learning_rate": 1.0827092668992529e-05, "loss": 0.1874, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.3220980140807832, "learning_rate": 1.077687414070869e-05, "loss": 0.2139, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.34437235618862705, "learning_rate": 1.0726729360293451e-05, "loss": 0.2101, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.3290158102554546, "learning_rate": 1.0676658728703147e-05, "loss": 0.2143, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.33735890075493713, "learning_rate": 1.0626662646301198e-05, "loss": 0.2287, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.325136874633483, "learning_rate": 1.0576741512854958e-05, "loss": 0.2238, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.34133666109932803, "learning_rate": 1.052689572753247e-05, "loss": 0.2083, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.32786216871058554, "learning_rate": 1.0477125688899328e-05, "loss": 0.2027, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.32775960337222904, "learning_rate": 1.0427431794915406e-05, "loss": 0.2241, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.3338067064027903, "learning_rate": 1.0377814442931769e-05, "loss": 0.2165, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.3307764651165638, "learning_rate": 1.0328274029687439e-05, "loss": 0.2216, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.3168930812511843, "learning_rate": 1.0278810951306253e-05, "loss": 0.2297, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.33748255836557906, "learning_rate": 1.0229425603293647e-05, "loss": 0.212, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.33690034256235046, "learning_rate": 1.0180118380533558e-05, "loss": 0.1894, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.3292893914274704, "learning_rate": 1.0130889677285225e-05, "loss": 0.2213, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.3307139946375226, "learning_rate": 1.008173988718005e-05, "loss": 0.2247, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.341610491526979, "learning_rate": 1.0032669403218439e-05, "loss": 0.2074, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.3321620769406261, "learning_rate": 9.983678617766677e-06, "loss": 0.2317, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.32816870045511554, "learning_rate": 9.934767922553788e-06, "loss": 0.2183, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.33884482298667384, "learning_rate": 9.885937708668371e-06, "loss": 0.2194, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.3365648503989295, "learning_rate": 9.837188366555524e-06, "loss": 0.2159, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.3243581476449658, "learning_rate": 9.788520286013691e-06, "loss": 0.2299, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.32577015067515736, "learning_rate": 9.739933856191537e-06, "loss": 0.2084, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.3183842989495928, "learning_rate": 9.691429465584866e-06, "loss": 0.2126, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.3161881081078381, "learning_rate": 9.643007502033492e-06, "loss": 0.2276, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.3288692114245841, "learning_rate": 9.594668352718152e-06, "loss": 0.2343, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.3235226025684495, "learning_rate": 9.546412404157383e-06, "loss": 0.2192, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.3095609690194547, "learning_rate": 9.498240042204471e-06, "loss": 0.2305, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.3439824637345479, "learning_rate": 9.450151652044339e-06, "loss": 0.2278, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.32979721657350325, "learning_rate": 9.402147618190472e-06, "loss": 0.2296, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.3227691664890885, "learning_rate": 9.354228324481841e-06, "loss": 0.2104, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.3391387192664387, "learning_rate": 9.306394154079852e-06, "loss": 0.2096, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.3381621143720419, "learning_rate": 9.258645489465254e-06, "loss": 0.2256, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.33727650270975, "learning_rate": 9.21098271243509e-06, "loss": 0.209, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.329357101474831, "learning_rate": 9.163406204099659e-06, "loss": 0.1923, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.3265875354089689, "learning_rate": 9.115916344879452e-06, "loss": 0.2122, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.32612799717499574, "learning_rate": 9.068513514502126e-06, "loss": 0.2052, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.32714075874694787, "learning_rate": 9.021198091999439e-06, "loss": 0.2119, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.3161185951262001, "learning_rate": 8.973970455704251e-06, "loss": 0.1937, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.3136634818866269, "learning_rate": 8.926830983247495e-06, "loss": 0.2173, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.3359418343072537, "learning_rate": 8.879780051555116e-06, "loss": 0.1941, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.31854474549510764, "learning_rate": 8.83281803684512e-06, "loss": 0.2087, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.33534423553217924, "learning_rate": 8.785945314624532e-06, "loss": 0.2014, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.3233599479709358, "learning_rate": 8.739162259686385e-06, "loss": 0.2256, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.31790540219437885, "learning_rate": 8.692469246106734e-06, "loss": 0.2081, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.3091884527295142, "learning_rate": 8.645866647241677e-06, "loss": 0.2108, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.32892007699708026, "learning_rate": 8.599354835724348e-06, "loss": 0.232, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.3162120705053787, "learning_rate": 8.552934183461958e-06, "loss": 0.2155, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.33580126065970956, "learning_rate": 8.506605061632805e-06, "loss": 0.2036, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.3246407895830403, "learning_rate": 8.460367840683308e-06, "loss": 0.2029, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.32805196036968626, "learning_rate": 8.414222890325065e-06, "loss": 0.226, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.334915259100869, "learning_rate": 8.368170579531855e-06, "loss": 0.2036, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.32887237256886154, "learning_rate": 8.322211276536733e-06, "loss": 0.1969, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.322893196074902, "learning_rate": 8.27634534882907e-06, "loss": 0.2285, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.31904578484538887, "learning_rate": 8.230573163151585e-06, "loss": 0.1957, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.3244936053064295, "learning_rate": 8.184895085497466e-06, "loss": 0.2128, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.32526690229353605, "learning_rate": 8.139311481107401e-06, "loss": 0.2136, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.32868452951677135, "learning_rate": 8.093822714466686e-06, "loss": 0.2084, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.34527684485684873, "learning_rate": 8.048429149302271e-06, "loss": 0.1913, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.320503403971248, "learning_rate": 8.003131148579902e-06, "loss": 0.2306, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.3144374930719935, "learning_rate": 7.957929074501182e-06, "loss": 0.2128, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.3319112402413119, "learning_rate": 7.912823288500695e-06, "loss": 0.2258, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.3282728839975709, "learning_rate": 7.867814151243102e-06, "loss": 0.2105, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.32422750523942623, "learning_rate": 7.822902022620267e-06, "loss": 0.1956, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.32261620136252456, "learning_rate": 7.778087261748377e-06, "loss": 0.2113, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.32903879518090007, "learning_rate": 7.733370226965056e-06, "loss": 0.2116, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.32168156994347324, "learning_rate": 7.688751275826527e-06, "loss": 0.2185, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.3259192925819375, "learning_rate": 7.644230765104735e-06, "loss": 0.1908, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.3386091569963155, "learning_rate": 7.599809050784502e-06, "loss": 0.2109, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.3272304077118077, "learning_rate": 7.555486488060661e-06, "loss": 0.195, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.3213948725079133, "learning_rate": 7.511263431335249e-06, "loss": 0.202, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.32856973512277415, "learning_rate": 7.467140234214656e-06, "loss": 0.2184, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.3280092373442192, "learning_rate": 7.423117249506777e-06, "loss": 0.2236, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.32457886054805546, "learning_rate": 7.379194829218231e-06, "loss": 0.2132, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.32485926307239965, "learning_rate": 7.335373324551518e-06, "loss": 0.1971, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.3174731978718754, "learning_rate": 7.291653085902224e-06, "loss": 0.2198, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.3161522236048498, "learning_rate": 7.248034462856213e-06, "loss": 0.2187, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.32114295096750045, "learning_rate": 7.20451780418683e-06, "loss": 0.2252, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.31991459703985975, "learning_rate": 7.161103457852128e-06, "loss": 0.2118, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.3187117990194774, "learning_rate": 7.117791770992046e-06, "loss": 0.2074, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.3165942247408342, "learning_rate": 7.074583089925688e-06, "loss": 0.2204, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.3235101957666249, "learning_rate": 7.0314777601485155e-06, "loss": 0.2131, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.3392841286432187, "learning_rate": 6.988476126329604e-06, "loss": 0.2243, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.31618432822417813, "learning_rate": 6.945578532308857e-06, "loss": 0.2135, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.3035951074691598, "learning_rate": 6.902785321094301e-06, "loss": 0.2036, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.32497919654411506, "learning_rate": 6.8600968348593115e-06, "loss": 0.2229, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.3220205442970766, "learning_rate": 6.817513414939892e-06, "loss": 0.2233, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.31993223200027865, "learning_rate": 6.775035401831924e-06, "loss": 0.2148, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.30864315909682516, "learning_rate": 6.732663135188473e-06, "loss": 0.2127, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.3201536619609025, "learning_rate": 6.690396953817055e-06, "loss": 0.1963, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.32801185047070125, "learning_rate": 6.648237195676927e-06, "loss": 0.1891, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.3216859239143471, "learning_rate": 6.606184197876395e-06, "loss": 0.1977, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.3250550157574579, "learning_rate": 6.564238296670109e-06, "loss": 0.2089, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.3395290044595123, "learning_rate": 6.52239982745638e-06, "loss": 0.2077, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.3268203936640536, "learning_rate": 6.480669124774484e-06, "loss": 0.2134, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.33472078628353985, "learning_rate": 6.439046522302013e-06, "loss": 0.2159, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.3155364765980969, "learning_rate": 6.397532352852191e-06, "loss": 0.2165, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.3217278391413827, "learning_rate": 6.356126948371202e-06, "loss": 0.2149, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.32419560068676573, "learning_rate": 6.314830639935559e-06, "loss": 0.1985, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.3089569813200013, "learning_rate": 6.273643757749448e-06, "loss": 0.2255, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.32138634688131196, "learning_rate": 6.2325666311420856e-06, "loss": 0.2254, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.31133397998902546, "learning_rate": 6.1915995885650675e-06, "loss": 0.2008, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.32559921517299695, "learning_rate": 6.150742957589784e-06, "loss": 0.2281, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.32916081643048006, "learning_rate": 6.109997064904774e-06, "loss": 0.2096, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.3240658226233956, "learning_rate": 6.069362236313092e-06, "loss": 0.2207, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.3261485428670914, "learning_rate": 6.0288387967297565e-06, "loss": 0.2074, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.33151536381803964, "learning_rate": 5.988427070179108e-06, "loss": 0.1966, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.3222207743595876, "learning_rate": 5.948127379792234e-06, "loss": 0.2271, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.31787225791273166, "learning_rate": 5.90794004780439e-06, "loss": 0.2165, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.3132021257930102, "learning_rate": 5.867865395552405e-06, "loss": 0.2153, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.3218660488619501, "learning_rate": 5.8279037434721364e-06, "loss": 0.1994, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.31687550772341655, "learning_rate": 5.788055411095892e-06, "loss": 0.221, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.3113733876689078, "learning_rate": 5.7483207170498625e-06, "loss": 0.1989, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.3189169379660964, "learning_rate": 5.708699979051613e-06, "loss": 0.215, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.3125799111531271, "learning_rate": 5.66919351390751e-06, "loss": 0.2037, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.3324316051452499, "learning_rate": 5.629801637510188e-06, "loss": 0.2061, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.32520199023465834, "learning_rate": 5.590524664836043e-06, "loss": 0.2134, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.32459265619662975, "learning_rate": 5.551362909942708e-06, "loss": 0.19, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.3080291982245285, "learning_rate": 5.51231668596653e-06, "loss": 0.2114, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.325326935411513, "learning_rate": 5.47338630512007e-06, "loss": 0.2198, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.3113491386338541, "learning_rate": 5.434572078689617e-06, "loss": 0.2342, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.3130515807828786, "learning_rate": 5.395874317032694e-06, "loss": 0.2109, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.32249120152166183, "learning_rate": 5.357293329575573e-06, "loss": 0.2106, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.32515633148327255, "learning_rate": 5.318829424810797e-06, "loss": 0.2261, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.31574853128634345, "learning_rate": 5.280482910294728e-06, "loss": 0.2128, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.3248490027260798, "learning_rate": 5.242254092645078e-06, "loss": 0.2079, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.3086868477057686, "learning_rate": 5.2041432775384445e-06, "loss": 0.2117, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.31074343407401156, "learning_rate": 5.166150769707892e-06, "loss": 0.2174, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.3080351214458713, "learning_rate": 5.128276872940503e-06, "loss": 0.2222, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.3225179338184548, "learning_rate": 5.090521890074953e-06, "loss": 0.1964, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.3199094825487691, "learning_rate": 5.0528861229990675e-06, "loss": 0.2058, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.31204572097793104, "learning_rate": 5.015369872647442e-06, "loss": 0.2164, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.32165079292233717, "learning_rate": 4.9779734389990195e-06, "loss": 0.1912, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.32220550563568656, "learning_rate": 4.940697121074675e-06, "loss": 0.1938, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.32330754337990564, "learning_rate": 4.903541216934864e-06, "loss": 0.2067, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.3100178341102079, "learning_rate": 4.8665060236772e-06, "loss": 0.2027, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.3154481764154965, "learning_rate": 4.829591837434102e-06, "loss": 0.2118, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.3104233262229767, "learning_rate": 4.792798953370424e-06, "loss": 0.2104, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.3124751925262657, "learning_rate": 4.756127665681083e-06, "loss": 0.2199, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.31477782122579057, "learning_rate": 4.719578267588725e-06, "loss": 0.2177, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.30674585167625673, "learning_rate": 4.6831510513413525e-06, "loss": 0.2138, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4559781868849412, "learning_rate": 4.6468463082100176e-06, "loss": 0.1663, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.40094079318892695, "learning_rate": 4.610664328486485e-06, "loss": 0.1397, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.29408004398565146, "learning_rate": 4.5746054014809e-06, "loss": 0.1553, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.25830405882415275, "learning_rate": 4.5386698155194766e-06, "loss": 0.1468, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.33863852424534513, "learning_rate": 4.502857857942204e-06, "loss": 0.157, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.43090456321108495, "learning_rate": 4.467169815100549e-06, "loss": 0.1672, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3993421638145693, "learning_rate": 4.431605972355137e-06, "loss": 0.1255, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.38876365815436803, "learning_rate": 4.396166614073516e-06, "loss": 0.1645, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.32588917824457897, "learning_rate": 4.360852023627846e-06, "loss": 0.1646, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3060196269614054, "learning_rate": 4.325662483392656e-06, "loss": 0.1536, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.32457288279235036, "learning_rate": 4.29059827474257e-06, "loss": 0.1526, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.32493228252050754, "learning_rate": 4.255659678050063e-06, "loss": 0.1484, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.33640426937000345, "learning_rate": 4.22084697268323e-06, "loss": 0.1537, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.27389525546040155, "learning_rate": 4.186160437003535e-06, "loss": 0.1538, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.2939898560648548, "learning_rate": 4.151600348363582e-06, "loss": 0.1883, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.30332575036272513, "learning_rate": 4.11716698310493e-06, "loss": 0.1642, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.3093516887821109, "learning_rate": 4.082860616555848e-06, "loss": 0.1486, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.2928494619499575, "learning_rate": 4.048681523029125e-06, "loss": 0.1474, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.28306050339181704, "learning_rate": 4.014629975819882e-06, "loss": 0.1449, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.28094166903722484, "learning_rate": 3.9807062472033855e-06, "loss": 0.1699, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2677021608716976, "learning_rate": 3.94691060843287e-06, "loss": 0.1321, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.3107281325382739, "learning_rate": 3.913243329737353e-06, "loss": 0.1688, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.2815624761917089, "learning_rate": 3.879704680319503e-06, "loss": 0.1444, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.27729243597461284, "learning_rate": 3.846294928353471e-06, "loss": 0.1436, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.28284361655789964, "learning_rate": 3.8130143409827345e-06, "loss": 0.1632, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.27140611842911794, "learning_rate": 3.7798631843179887e-06, "loss": 0.1389, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2791215585857704, "learning_rate": 3.7468417234349973e-06, "loss": 0.1482, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.28014713009094616, "learning_rate": 3.7139502223724823e-06, "loss": 0.1663, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2690364446801268, "learning_rate": 3.6811889441300095e-06, "loss": 0.145, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.26151342273906514, "learning_rate": 3.648558150665886e-06, "loss": 0.1563, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.2628450621059637, "learning_rate": 3.616058102895075e-06, "loss": 0.1509, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.28542594675695654, "learning_rate": 3.583689060687079e-06, "loss": 0.1513, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.27874157630686824, "learning_rate": 3.5514512828639023e-06, "loss": 0.1454, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.25845616780793795, "learning_rate": 3.51934502719796e-06, "loss": 0.1581, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.25438059561306103, "learning_rate": 3.4873705504100185e-06, "loss": 0.1545, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.26170047912815714, "learning_rate": 3.4555281081671345e-06, "loss": 0.1386, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.25793489578784756, "learning_rate": 3.4238179550806326e-06, "loss": 0.1551, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.24931148543011863, "learning_rate": 3.3922403447040497e-06, "loss": 0.1446, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.26757215361393416, "learning_rate": 3.3607955295311247e-06, "loss": 0.1312, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2533419325668877, "learning_rate": 3.32948376099375e-06, "loss": 0.1867, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.24573479684084687, "learning_rate": 3.2983052894599976e-06, "loss": 0.1466, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.27465628573807843, "learning_rate": 3.2672603642320945e-06, "loss": 0.1545, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2579903904236158, "learning_rate": 3.236349233544438e-06, "loss": 0.1627, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2719839439933177, "learning_rate": 3.205572144561604e-06, "loss": 0.1598, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.25636447061577966, "learning_rate": 3.174929343376374e-06, "loss": 0.1508, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.26133662452930245, "learning_rate": 3.1444210750077777e-06, "loss": 0.1499, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.26402208859325216, "learning_rate": 3.1140475833991046e-06, "loss": 0.159, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.2563898153148043, "learning_rate": 3.0838091114159895e-06, "loss": 0.155, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2422728823545693, "learning_rate": 3.0537059008444524e-06, "loss": 0.1571, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2640597067503048, "learning_rate": 3.0237381923889563e-06, "loss": 0.1426, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.25800957761027493, "learning_rate": 2.9939062256704997e-06, "loss": 0.1614, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.2572476483082985, "learning_rate": 2.964210239224696e-06, "loss": 0.1401, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.26519612372824575, "learning_rate": 2.934650470499869e-06, "loss": 0.1344, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.24402297357091554, "learning_rate": 2.905227155855128e-06, "loss": 0.1397, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2615288182123599, "learning_rate": 2.875940530558519e-06, "loss": 0.1652, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2582387898869141, "learning_rate": 2.8467908287851154e-06, "loss": 0.1285, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.2560864761892997, "learning_rate": 2.8177782836151603e-06, "loss": 0.1664, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.26378111820757344, "learning_rate": 2.7889031270321874e-06, "loss": 0.1606, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.25626453538654204, "learning_rate": 2.760165589921184e-06, "loss": 0.151, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.2462783535432481, "learning_rate": 2.7315659020667305e-06, "loss": 0.1183, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2648894204768788, "learning_rate": 2.703104292151164e-06, "loss": 0.1692, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.2593197237890005, "learning_rate": 2.6747809877527607e-06, "loss": 0.1576, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.254196822013425, "learning_rate": 2.6465962153439082e-06, "loss": 0.1456, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.25965183463415176, "learning_rate": 2.618550200289303e-06, "loss": 0.1454, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2592373773203586, "learning_rate": 2.59064316684412e-06, "loss": 0.1607, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.2496466522186927, "learning_rate": 2.562875338152264e-06, "loss": 0.1496, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2595414459397966, "learning_rate": 2.5352469362445552e-06, "loss": 0.1795, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2596004965609304, "learning_rate": 2.5077581820369523e-06, "loss": 0.1551, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.2566224035859454, "learning_rate": 2.480409295328803e-06, "loss": 0.1397, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.28581448973293444, "learning_rate": 2.45320049480108e-06, "loss": 0.125, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.2657770197971591, "learning_rate": 2.4261319980146293e-06, "loss": 0.1543, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.25463867902866283, "learning_rate": 2.399204021408421e-06, "loss": 0.1485, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.26558376023688224, "learning_rate": 2.3724167802978395e-06, "loss": 0.1622, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.2686409438759538, "learning_rate": 2.3457704888729625e-06, "loss": 0.1394, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.263189923420297, "learning_rate": 2.3192653601968162e-06, "loss": 0.1609, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.25880321205883117, "learning_rate": 2.2929016062037057e-06, "loss": 0.1514, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2542462646040968, "learning_rate": 2.2666794376975055e-06, "loss": 0.1571, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2650632613317617, "learning_rate": 2.24059906434998e-06, "loss": 0.1693, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.2618953548986103, "learning_rate": 2.214660694699091e-06, "loss": 0.1466, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.25369956554776035, "learning_rate": 2.188864536147355e-06, "loss": 0.1393, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2676649722653889, "learning_rate": 2.1632107949601757e-06, "loss": 0.1462, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.25639247636623785, "learning_rate": 2.137699676264171e-06, "loss": 0.1508, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.2512237802575331, "learning_rate": 2.1123313840455738e-06, "loss": 0.1323, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.2538677052557193, "learning_rate": 2.08710612114857e-06, "loss": 0.1576, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2631895743400782, "learning_rate": 2.0620240892736953e-06, "loss": 0.1321, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.26339105998026685, "learning_rate": 2.0370854889762e-06, "loss": 0.1668, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.2584531811585903, "learning_rate": 2.0122905196644726e-06, "loss": 0.1434, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.2487816718524478, "learning_rate": 1.987639379598427e-06, "loss": 0.135, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.24644844484061323, "learning_rate": 1.963132265887919e-06, "loss": 0.1531, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.2536039828397838, "learning_rate": 1.9387693744911784e-06, "loss": 0.1518, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.260510732197341, "learning_rate": 1.9145509002132368e-06, "loss": 0.1614, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.27248912450287227, "learning_rate": 1.8904770367043723e-06, "loss": 0.1598, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.25984657297830044, "learning_rate": 1.8665479764585504e-06, "loss": 0.1758, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.27989968529032716, "learning_rate": 1.8427639108118977e-06, "loss": 0.1649, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2610318343811418, "learning_rate": 1.8191250299411755e-06, "loss": 0.1665, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2465969068540887, "learning_rate": 1.7956315228622446e-06, "loss": 0.1316, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2542116613780092, "learning_rate": 1.7722835774285553e-06, "loss": 0.1426, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2465462336919422, "learning_rate": 1.7490813803296624e-06, "loss": 0.1444, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.24823302249442372, "learning_rate": 1.726025117089718e-06, "loss": 0.147, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.25353008938258986, "learning_rate": 1.70311497206598e-06, "loss": 0.1363, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2576712398838385, "learning_rate": 1.6803511284473638e-06, "loss": 0.1549, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.2606393772326081, "learning_rate": 1.6577337682529538e-06, "loss": 0.1421, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2608339952087738, "learning_rate": 1.6352630723305617e-06, "loss": 0.1428, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.25905278519005415, "learning_rate": 1.612939220355272e-06, "loss": 0.157, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.25409614001904435, "learning_rate": 1.5907623908280112e-06, "loss": 0.1453, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.27491758355066687, "learning_rate": 1.568732761074121e-06, "loss": 0.1273, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.2793502441700334, "learning_rate": 1.5468505072419237e-06, "loss": 0.1628, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.26256378446820205, "learning_rate": 1.5251158043013448e-06, "loss": 0.1369, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.28092220275904595, "learning_rate": 1.5035288260424885e-06, "loss": 0.1541, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.25220612089515043, "learning_rate": 1.4820897450742623e-06, "loss": 0.1514, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.26235823760026405, "learning_rate": 1.4607987328229767e-06, "loss": 0.1524, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.25516419498238824, "learning_rate": 1.4396559595310056e-06, "loss": 0.1496, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.25925258614724794, "learning_rate": 1.4186615942553973e-06, "loss": 0.1709, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2546815747820447, "learning_rate": 1.3978158048665424e-06, "loss": 0.1626, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.25992944967218085, "learning_rate": 1.3771187580468115e-06, "loss": 0.1446, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.25927815283910116, "learning_rate": 1.3565706192892392e-06, "loss": 0.158, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.25714246694234827, "learning_rate": 1.3361715528961993e-06, "loss": 0.1666, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2622495180952866, "learning_rate": 1.3159217219780817e-06, "loss": 0.1596, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.24410423252728938, "learning_rate": 1.2958212884519949e-06, "loss": 0.1337, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.27243126182284183, "learning_rate": 1.2758704130404675e-06, "loss": 0.1382, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.2607572320142179, "learning_rate": 1.2560692552701738e-06, "loss": 0.1425, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.26661280205512783, "learning_rate": 1.2364179734706382e-06, "loss": 0.1354, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.260932064754177, "learning_rate": 1.2169167247729852e-06, "loss": 0.1735, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.24977736261431058, "learning_rate": 1.1975656651086864e-06, "loss": 0.1328, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.24386552178519277, "learning_rate": 1.1783649492082926e-06, "loss": 0.1479, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.24963884968020858, "learning_rate": 1.1593147306002183e-06, "loss": 0.1411, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.25109801882046834, "learning_rate": 1.140415161609505e-06, "loss": 0.1752, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2631301147892363, "learning_rate": 1.121666393356604e-06, "loss": 0.1432, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.25172068710626266, "learning_rate": 1.1030685757561632e-06, "loss": 0.158, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2508335143918096, "learning_rate": 1.0846218575158373e-06, "loss": 0.1295, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.25955735188285134, "learning_rate": 1.066326386135097e-06, "loss": 0.1601, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.25874129187195444, "learning_rate": 1.0481823079040398e-06, "loss": 0.1447, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.26334264363431087, "learning_rate": 1.0301897679022344e-06, "loss": 0.1393, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.25834496250332417, "learning_rate": 1.0123489099975491e-06, "loss": 0.164, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2703348421158148, "learning_rate": 9.9465987684501e-07, "loss": 0.1505, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.25106199747521607, "learning_rate": 9.771228098856534e-07, "loss": 0.1439, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.25650930337855093, "learning_rate": 9.597378493454013e-07, "loss": 0.1357, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.25236023648493894, "learning_rate": 9.425051342339353e-07, "loss": 0.1443, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.2585696462311496, "learning_rate": 9.254248023435864e-07, "loss": 0.1527, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.24869419969536444, "learning_rate": 9.084969902482288e-07, "loss": 0.1349, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.2587375638980896, "learning_rate": 8.917218333021993e-07, "loss": 0.1536, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.25958189552740607, "learning_rate": 8.750994656392109e-07, "loss": 0.1374, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.25887469817998127, "learning_rate": 8.58630020171265e-07, "loss": 0.1331, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2678586406812538, "learning_rate": 8.423136285876099e-07, "loss": 0.142, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2622007155315305, "learning_rate": 8.26150421353682e-07, "loss": 0.1532, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2629435472897881, "learning_rate": 8.101405277100549e-07, "loss": 0.1484, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2619407826606692, "learning_rate": 7.942840756714077e-07, "loss": 0.1498, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.25796289629014146, "learning_rate": 7.785811920255093e-07, "loss": 0.1299, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.25263378892052396, "learning_rate": 7.630320023322024e-07, "loss": 0.1511, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.2663513413774312, "learning_rate": 7.476366309223903e-07, "loss": 0.1527, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.26442880167680644, "learning_rate": 7.323952008970537e-07, "loss": 0.1528, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2580725455925201, "learning_rate": 7.173078341262618e-07, "loss": 0.1528, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2472130008301396, "learning_rate": 7.023746512481989e-07, "loss": 0.1444, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2648649094787431, "learning_rate": 6.875957716681902e-07, "loss": 0.1641, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.25848007072017176, "learning_rate": 6.729713135577687e-07, "loss": 0.1629, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2564396725021176, "learning_rate": 6.585013938537143e-07, "loss": 0.1591, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2590569599916796, "learning_rate": 6.441861282571115e-07, "loss": 0.1641, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.25103886881327964, "learning_rate": 6.300256312324471e-07, "loss": 0.1473, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2542777542088407, "learning_rate": 6.160200160066776e-07, "loss": 0.1557, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.2542219566232063, "learning_rate": 6.021693945683327e-07, "loss": 0.1559, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.2524884198213547, "learning_rate": 5.884738776666044e-07, "loss": 0.1715, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.26416746237885197, "learning_rate": 5.749335748104878e-07, "loss": 0.159, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.25368130736457783, "learning_rate": 5.615485942678778e-07, "loss": 0.1366, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.2559381695527933, "learning_rate": 5.483190430647289e-07, "loss": 0.1512, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.25737025359706633, "learning_rate": 5.352450269841747e-07, "loss": 0.1772, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.2526801646008372, "learning_rate": 5.22326650565701e-07, "loss": 0.1407, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2533950404455829, "learning_rate": 5.095640171043048e-07, "loss": 0.1631, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.253844967776762, "learning_rate": 4.969572286496594e-07, "loss": 0.1576, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.25693031324745935, "learning_rate": 4.845063860053079e-07, "loss": 0.1432, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.23952805113151102, "learning_rate": 4.7221158872785997e-07, "loss": 0.1437, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.24353617298810995, "learning_rate": 4.600729351261857e-07, "loss": 0.1349, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.25342146173128405, "learning_rate": 4.4809052226063355e-07, "loss": 0.1702, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.24907976138486596, "learning_rate": 4.3626444594226046e-07, "loss": 0.1414, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.25097201858048096, "learning_rate": 4.245948007320588e-07, "loss": 0.1465, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.25951714699744577, "learning_rate": 4.130816799401971e-07, "loss": 0.1418, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.25246351497334035, "learning_rate": 4.017251756252827e-07, "loss": 0.1627, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.26065554979410893, "learning_rate": 3.9052537859362473e-07, "loss": 0.1616, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2604830721485494, "learning_rate": 3.7948237839849687e-07, "loss": 0.1593, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.25398350996540453, "learning_rate": 3.6859626333943797e-07, "loss": 0.1511, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.2591988736220829, "learning_rate": 3.578671204615347e-07, "loss": 0.1626, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.259734696467066, "learning_rate": 3.472950355547267e-07, "loss": 0.139, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.2384713118686992, "learning_rate": 3.3688009315312244e-07, "loss": 0.167, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2553774028079394, "learning_rate": 3.266223765343224e-07, "loss": 0.1513, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.26626345212233415, "learning_rate": 3.16521967718757e-07, "loss": 0.1656, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.2528974037148508, "learning_rate": 3.0657894746902726e-07, "loss": 0.1527, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.2572582941088505, "learning_rate": 2.9679339528925654e-07, "loss": 0.1495, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.25440075754282476, "learning_rate": 2.871653894244597e-07, "loss": 0.1502, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.26663923624762415, "learning_rate": 2.7769500685991266e-07, "loss": 0.154, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2537421970917347, "learning_rate": 2.683823233205485e-07, "loss": 0.1453, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.25023306363838577, "learning_rate": 2.592274132703287e-07, "loss": 0.1457, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.25316925771167675, "learning_rate": 2.502303499116754e-07, "loss": 0.1414, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.2540148185405954, "learning_rate": 2.413912051848666e-07, "loss": 0.1483, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.2694609122240606, "learning_rate": 2.3271004976746613e-07, "loss": 0.1399, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2551929522656687, "learning_rate": 2.2418695307376393e-07, "loss": 0.1616, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.25201016843121277, "learning_rate": 2.1582198325420968e-07, "loss": 0.1401, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.2560565686085204, "learning_rate": 2.0761520719488447e-07, "loss": 0.1498, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.2661454655891785, "learning_rate": 1.9956669051694798e-07, "loss": 0.1543, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.24789286446516356, "learning_rate": 1.916764975761254e-07, "loss": 0.1476, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2545845733316667, "learning_rate": 1.839446914621923e-07, "loss": 0.1477, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.2460084035018459, "learning_rate": 1.7637133399845962e-07, "loss": 0.1338, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.2434408244257997, "learning_rate": 1.6895648574129397e-07, "loss": 0.1578, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.25050558294976044, "learning_rate": 1.6170020597962465e-07, "loss": 0.1576, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.25434337467569457, "learning_rate": 1.5460255273447078e-07, "loss": 0.1425, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.2550070123825045, "learning_rate": 1.4766358275847715e-07, "loss": 0.1322, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.25767294865651, "learning_rate": 1.4088335153546573e-07, "loss": 0.172, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.25816608717430434, "learning_rate": 1.3426191327998496e-07, "loss": 0.1675, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.25077739809729205, "learning_rate": 1.277993209368744e-07, "loss": 0.1541, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.24864883361189496, "learning_rate": 1.214956261808542e-07, "loss": 0.1376, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.24905106216075, "learning_rate": 1.1535087941609846e-07, "loss": 0.1613, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.25887040619451296, "learning_rate": 1.0936512977583802e-07, "loss": 0.1453, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.25382341535697245, "learning_rate": 1.0353842512196732e-07, "loss": 0.1564, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.2530365908530742, "learning_rate": 9.787081204466253e-08, "loss": 0.1321, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.25132102231726927, "learning_rate": 9.236233586200627e-08, "loss": 0.1595, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.25965431021880103, "learning_rate": 8.70130406196279e-08, "loss": 0.1779, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2607294799793227, "learning_rate": 8.182296909035047e-08, "loss": 0.1527, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.2568830843997916, "learning_rate": 7.679216277384439e-08, "loss": 0.1479, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2471404178250613, "learning_rate": 7.19206618963053e-08, "loss": 0.1573, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.2512329133526533, "learning_rate": 6.720850541012347e-08, "loss": 0.16, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.2502165875654458, "learning_rate": 6.265573099357714e-08, "loss": 0.1239, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.258388670142706, "learning_rate": 5.826237505053067e-08, "loss": 0.1653, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.25096718535288576, "learning_rate": 5.4028472710137e-08, "loss": 0.1597, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.2573635521162921, "learning_rate": 4.9954057826571146e-08, "loss": 0.1449, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2561703405335946, "learning_rate": 4.6039162978743776e-08, "loss": 0.1438, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.25815836482027776, "learning_rate": 4.228381947004812e-08, "loss": 0.134, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.25986358733677495, "learning_rate": 3.868805732811343e-08, "loss": 0.1277, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.2508680792252071, "learning_rate": 3.525190530455636e-08, "loss": 0.1692, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.25960811713088705, "learning_rate": 3.197539087475887e-08, "loss": 0.1517, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.25885827883115275, "learning_rate": 2.8858540237641786e-08, "loss": 0.1589, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.24917391327612518, "learning_rate": 2.5901378315458247e-08, "loss": 0.1693, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.2495438490183108, "learning_rate": 2.3103928753598347e-08, "loss": 0.1455, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.25517259049656127, "learning_rate": 2.0466213920393718e-08, "loss": 0.1442, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.26068222466369156, "learning_rate": 1.7988254906942115e-08, "loss": 0.1572, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.2530037406200602, "learning_rate": 1.5670071526936447e-08, "loss": 0.1522, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2495243420472749, "learning_rate": 1.3511682316509344e-08, "loss": 0.1539, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.2409905186527118, "learning_rate": 1.1513104534086605e-08, "loss": 0.1366, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.2555394373527456, "learning_rate": 9.67435416023843e-09, "loss": 0.1303, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.25399910624986155, "learning_rate": 7.995445897566178e-09, "loss": 0.1518, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.24747129678441548, "learning_rate": 6.476393170578021e-09, "loss": 0.1391, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.2557515670610242, "learning_rate": 5.11720812557348e-09, "loss": 0.1444, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.24900623153801027, "learning_rate": 3.917901630563492e-09, "loss": 0.1547, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2428827241667347, "learning_rate": 2.878483275170485e-09, "loss": 0.147, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.25512054869815076, "learning_rate": 1.998961370555108e-09, "loss": 0.1804, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.24528457694596403, "learning_rate": 1.2793429493518361e-09, "loss": 0.1449, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2488724954225418, "learning_rate": 7.196337656112384e-10, "loss": 0.1563, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.24172694374380183, "learning_rate": 3.198382947511292e-10, "loss": 0.1524, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.2482286627890261, "learning_rate": 7.995973352770137e-11, "loss": 0.1559, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.24657687179451515, "learning_rate": 0.0, "loss": 0.1282, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.8323350087155057e+18, "train_loss": 0.3733112201335942, "train_runtime": 21298.2648, "train_samples_per_second": 7.418, "train_steps_per_second": 0.058 } ], "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": 1.8323350087155057e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }