{ "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": 6.610122734708396, "learning_rate": 3.2258064516129035e-07, "loss": 0.8389, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.680889971093538, "learning_rate": 6.451612903225807e-07, "loss": 0.8523, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.45264728605718, "learning_rate": 9.67741935483871e-07, "loss": 0.8355, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 5.879862503194777, "learning_rate": 1.2903225806451614e-06, "loss": 0.7782, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.010936153388489, "learning_rate": 1.6129032258064516e-06, "loss": 0.836, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.641642788328457, "learning_rate": 1.935483870967742e-06, "loss": 0.7953, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.216427552775226, "learning_rate": 2.2580645161290324e-06, "loss": 0.7625, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 3.994996012823407, "learning_rate": 2.580645161290323e-06, "loss": 0.7668, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.4136788224058314, "learning_rate": 2.903225806451613e-06, "loss": 0.7405, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.1078954877066733, "learning_rate": 3.225806451612903e-06, "loss": 0.739, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 1.926600464609793, "learning_rate": 3.548387096774194e-06, "loss": 0.714, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.782454634755271, "learning_rate": 3.870967741935484e-06, "loss": 0.7212, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.146119762386726, "learning_rate": 4.193548387096774e-06, "loss": 0.7356, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.1722867268101185, "learning_rate": 4.516129032258065e-06, "loss": 0.7186, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.969231924162843, "learning_rate": 4.838709677419355e-06, "loss": 0.7096, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.1499925558201256, "learning_rate": 5.161290322580646e-06, "loss": 0.666, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.821996004397665, "learning_rate": 5.483870967741935e-06, "loss": 0.6652, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.1776210980616493, "learning_rate": 5.806451612903226e-06, "loss": 0.6578, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.4215834458217853, "learning_rate": 6.129032258064517e-06, "loss": 0.6341, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.2234000878538533, "learning_rate": 6.451612903225806e-06, "loss": 0.6257, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.38270981584675, "learning_rate": 6.774193548387097e-06, "loss": 0.6248, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.5083909782096425, "learning_rate": 7.096774193548388e-06, "loss": 0.5992, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.1726785781253062, "learning_rate": 7.4193548387096784e-06, "loss": 0.5985, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.865712972070702, "learning_rate": 7.741935483870968e-06, "loss": 0.6065, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.0148459393528662, "learning_rate": 8.064516129032258e-06, "loss": 0.6044, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.8004052123820944, "learning_rate": 8.387096774193549e-06, "loss": 0.5684, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.7462992798503781, "learning_rate": 8.70967741935484e-06, "loss": 0.5802, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8029824772265842, "learning_rate": 9.03225806451613e-06, "loss": 0.5556, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7058585958846497, "learning_rate": 9.35483870967742e-06, "loss": 0.5662, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.5206552662305312, "learning_rate": 9.67741935483871e-06, "loss": 0.5486, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.5984377041138851, "learning_rate": 1e-05, "loss": 0.5472, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7534709541016023, "learning_rate": 1.0322580645161291e-05, "loss": 0.5423, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.5954874563113924, "learning_rate": 1.0645161290322582e-05, "loss": 0.5324, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.45390462133089415, "learning_rate": 1.096774193548387e-05, "loss": 0.5418, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.6008702857954371, "learning_rate": 1.1290322580645164e-05, "loss": 0.5333, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.563164049909327, "learning_rate": 1.1612903225806453e-05, "loss": 0.5503, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5275445808309961, "learning_rate": 1.1935483870967743e-05, "loss": 0.5272, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.48070898888016117, "learning_rate": 1.2258064516129034e-05, "loss": 0.5322, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5023197654755079, "learning_rate": 1.2580645161290324e-05, "loss": 0.5209, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.4437477515632813, "learning_rate": 1.2903225806451613e-05, "loss": 0.5333, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.5521821013264376, "learning_rate": 1.3225806451612903e-05, "loss": 0.5353, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5517176647648457, "learning_rate": 1.3548387096774194e-05, "loss": 0.5179, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5827155845899091, "learning_rate": 1.3870967741935486e-05, "loss": 0.5171, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.4876096468779144, "learning_rate": 1.4193548387096776e-05, "loss": 0.5093, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.4586752051875495, "learning_rate": 1.4516129032258066e-05, "loss": 0.5197, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.4884716015837975, "learning_rate": 1.4838709677419357e-05, "loss": 0.4949, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.4464071484807167, "learning_rate": 1.5161290322580646e-05, "loss": 0.5194, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.406578540531465, "learning_rate": 1.5483870967741936e-05, "loss": 0.5132, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.40661600070711174, "learning_rate": 1.5806451612903226e-05, "loss": 0.4988, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.40113825103801615, "learning_rate": 1.6129032258064517e-05, "loss": 0.5079, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.3841943108257118, "learning_rate": 1.6451612903225807e-05, "loss": 0.4958, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.4480781407218796, "learning_rate": 1.6774193548387098e-05, "loss": 0.4892, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.3851466230415402, "learning_rate": 1.7096774193548388e-05, "loss": 0.4991, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5129612747182853, "learning_rate": 1.741935483870968e-05, "loss": 0.4983, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.45702123174705295, "learning_rate": 1.774193548387097e-05, "loss": 0.4955, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6579735236575188, "learning_rate": 1.806451612903226e-05, "loss": 0.5121, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6944091998140097, "learning_rate": 1.838709677419355e-05, "loss": 0.4951, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.4282207172317367, "learning_rate": 1.870967741935484e-05, "loss": 0.4792, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.4676511050581008, "learning_rate": 1.903225806451613e-05, "loss": 0.4947, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5267923231774341, "learning_rate": 1.935483870967742e-05, "loss": 0.4904, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5821260737922366, "learning_rate": 1.967741935483871e-05, "loss": 0.4992, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.5769242528230781, "learning_rate": 2e-05, "loss": 0.4919, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6198051411443473, "learning_rate": 2.0322580645161292e-05, "loss": 0.491, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.5602886484925671, "learning_rate": 2.0645161290322582e-05, "loss": 0.4853, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.5166069783866729, "learning_rate": 2.0967741935483873e-05, "loss": 0.4726, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.4260810821976313, "learning_rate": 2.1290322580645163e-05, "loss": 0.4782, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.544360371876142, "learning_rate": 2.161290322580645e-05, "loss": 0.4728, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.8019170458553776, "learning_rate": 2.193548387096774e-05, "loss": 0.493, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.8116578524522857, "learning_rate": 2.225806451612903e-05, "loss": 0.4795, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.7350860574215307, "learning_rate": 2.2580645161290328e-05, "loss": 0.4833, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.8325327220227787, "learning_rate": 2.2903225806451615e-05, "loss": 0.4864, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7489778388522171, "learning_rate": 2.3225806451612906e-05, "loss": 0.4818, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.6749011053892746, "learning_rate": 2.3548387096774196e-05, "loss": 0.475, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.8999490216024347, "learning_rate": 2.3870967741935486e-05, "loss": 0.4866, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 1.031643304756416, "learning_rate": 2.4193548387096777e-05, "loss": 0.499, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 1.0610546287893965, "learning_rate": 2.4516129032258067e-05, "loss": 0.4736, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.1257764541823152, "learning_rate": 2.4838709677419358e-05, "loss": 0.483, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7043685397708284, "learning_rate": 2.5161290322580648e-05, "loss": 0.4737, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 1.0354706821328719, "learning_rate": 2.548387096774194e-05, "loss": 0.4802, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.0884853209587069, "learning_rate": 2.5806451612903226e-05, "loss": 0.4763, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.6800247323571668, "learning_rate": 2.6129032258064516e-05, "loss": 0.4761, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.9258838197529374, "learning_rate": 2.6451612903225806e-05, "loss": 0.4727, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 1.292770864244904, "learning_rate": 2.6774193548387097e-05, "loss": 0.4902, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.5735341657794775, "learning_rate": 2.7096774193548387e-05, "loss": 0.471, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.4023445843661455, "learning_rate": 2.7419354838709678e-05, "loss": 0.4885, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.5406747432414969, "learning_rate": 2.774193548387097e-05, "loss": 0.4693, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 1.4100994672343616, "learning_rate": 2.8064516129032262e-05, "loss": 0.4838, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.5509858947294483, "learning_rate": 2.8387096774193552e-05, "loss": 0.484, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.4093158736616225, "learning_rate": 2.8709677419354843e-05, "loss": 0.4779, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.6086523742117058, "learning_rate": 2.9032258064516133e-05, "loss": 0.4772, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.3055786811605927, "learning_rate": 2.9354838709677423e-05, "loss": 0.4641, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.6508344680440138, "learning_rate": 2.9677419354838714e-05, "loss": 0.4702, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.0493306991741367, "learning_rate": 3.0000000000000004e-05, "loss": 0.4794, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.8645241677338816, "learning_rate": 3.032258064516129e-05, "loss": 0.454, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.7890890506098399, "learning_rate": 3.0645161290322585e-05, "loss": 0.4755, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.9983234729774684, "learning_rate": 3.096774193548387e-05, "loss": 0.4712, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.8504551641708518, "learning_rate": 3.1290322580645166e-05, "loss": 0.4757, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.7965043058606396, "learning_rate": 3.161290322580645e-05, "loss": 0.4644, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.6656980205698425, "learning_rate": 3.193548387096774e-05, "loss": 0.4631, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.765187067615285, "learning_rate": 3.2258064516129034e-05, "loss": 0.4656, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.0832230040679955, "learning_rate": 3.258064516129033e-05, "loss": 0.4716, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.2456396082460812, "learning_rate": 3.2903225806451614e-05, "loss": 0.4714, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.668778207326277, "learning_rate": 3.322580645161291e-05, "loss": 0.4709, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.8535933150379084, "learning_rate": 3.3548387096774195e-05, "loss": 0.4704, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.9846938780712534, "learning_rate": 3.387096774193549e-05, "loss": 0.483, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.0351196151443294, "learning_rate": 3.4193548387096776e-05, "loss": 0.4716, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.8265892298011066, "learning_rate": 3.451612903225807e-05, "loss": 0.4756, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.7390340841625834, "learning_rate": 3.483870967741936e-05, "loss": 0.4573, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9361941518302934, "learning_rate": 3.516129032258065e-05, "loss": 0.475, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.9523117701446471, "learning_rate": 3.548387096774194e-05, "loss": 0.4746, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.8599507011204582, "learning_rate": 3.5806451612903225e-05, "loss": 0.4695, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8822455630525604, "learning_rate": 3.612903225806452e-05, "loss": 0.4514, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.8925399897563657, "learning_rate": 3.6451612903225805e-05, "loss": 0.4721, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.9381249333393432, "learning_rate": 3.67741935483871e-05, "loss": 0.4641, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.9417062902897633, "learning_rate": 3.7096774193548386e-05, "loss": 0.4565, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.8591402289089146, "learning_rate": 3.741935483870968e-05, "loss": 0.463, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.8254306623365164, "learning_rate": 3.7741935483870974e-05, "loss": 0.4587, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.9565042697829245, "learning_rate": 3.806451612903226e-05, "loss": 0.4554, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.7814333233821303, "learning_rate": 3.8387096774193555e-05, "loss": 0.4728, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.7813947655958864, "learning_rate": 3.870967741935484e-05, "loss": 0.4672, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.7627976679884206, "learning_rate": 3.9032258064516135e-05, "loss": 0.4677, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.7032191864484347, "learning_rate": 3.935483870967742e-05, "loss": 0.4601, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7941207798923139, "learning_rate": 3.9677419354838716e-05, "loss": 0.4615, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7003880542389873, "learning_rate": 4e-05, "loss": 0.4385, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.716335465492181, "learning_rate": 3.9999920040266474e-05, "loss": 0.4875, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.1275237426204383, "learning_rate": 3.999968016170525e-05, "loss": 0.4632, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.770480449886897, "learning_rate": 3.9999280366234394e-05, "loss": 0.4613, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.6399722465104967, "learning_rate": 3.999872065705065e-05, "loss": 0.4413, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.8028787455233893, "learning_rate": 3.999800103862945e-05, "loss": 0.469, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.887937120986664, "learning_rate": 3.9997121516724834e-05, "loss": 0.4552, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.8185254093438448, "learning_rate": 3.999608209836944e-05, "loss": 0.4709, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.8274485574808588, "learning_rate": 3.999488279187443e-05, "loss": 0.4538, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.7554336199129452, "learning_rate": 3.9993523606829425e-05, "loss": 0.4552, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.678467161902449, "learning_rate": 3.9992004554102435e-05, "loss": 0.4517, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.6806992328086346, "learning_rate": 3.999032564583976e-05, "loss": 0.4495, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.5388751134777512, "learning_rate": 3.998848689546591e-05, "loss": 0.4504, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7140260589300537, "learning_rate": 3.9986488317683496e-05, "loss": 0.4599, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.7465194271239098, "learning_rate": 3.9984329928473067e-05, "loss": 0.4456, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.6264930781566671, "learning_rate": 3.998201174509306e-05, "loss": 0.4659, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.7879356465014431, "learning_rate": 3.997953378607961e-05, "loss": 0.4573, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6483142696149288, "learning_rate": 3.9976896071246403e-05, "loss": 0.4489, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.6365875421645684, "learning_rate": 3.997409862168454e-05, "loss": 0.4416, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.796155960009893, "learning_rate": 3.997114145976237e-05, "loss": 0.4489, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5606648110056653, "learning_rate": 3.9968024609125245e-05, "loss": 0.4566, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6853413733274585, "learning_rate": 3.996474809469545e-05, "loss": 0.4566, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.7914878817065129, "learning_rate": 3.996131194267189e-05, "loss": 0.4677, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.5575345036723298, "learning_rate": 3.995771618052995e-05, "loss": 0.4548, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.6849305026493887, "learning_rate": 3.9953960837021256e-05, "loss": 0.4567, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.533297617436128, "learning_rate": 3.995004594217343e-05, "loss": 0.4426, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.638397815886662, "learning_rate": 3.994597152728987e-05, "loss": 0.4743, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.7759926760104158, "learning_rate": 3.994173762494947e-05, "loss": 0.4499, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.5043682601585442, "learning_rate": 3.9937344269006424e-05, "loss": 0.4521, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.6172846032691269, "learning_rate": 3.993279149458988e-05, "loss": 0.4638, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.8247573386427393, "learning_rate": 3.9928079338103695e-05, "loss": 0.4511, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.5157320250753773, "learning_rate": 3.992320783722616e-05, "loss": 0.4468, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.8493307584118703, "learning_rate": 3.991817703090965e-05, "loss": 0.4463, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6727156891578825, "learning_rate": 3.991298695938038e-05, "loss": 0.445, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.49497010435413763, "learning_rate": 3.9907637664138e-05, "loss": 0.4532, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6498561020933611, "learning_rate": 3.990212918795534e-05, "loss": 0.4516, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.5755567268719427, "learning_rate": 3.9896461574878036e-05, "loss": 0.448, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.5622347659817468, "learning_rate": 3.989063487022416e-05, "loss": 0.4499, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5678084109356641, "learning_rate": 3.9884649120583903e-05, "loss": 0.4445, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5981260149421382, "learning_rate": 3.987850437381915e-05, "loss": 0.4659, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.5675713579270757, "learning_rate": 3.987220067906313e-05, "loss": 0.4602, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.5393080709508546, "learning_rate": 3.986573808672002e-05, "loss": 0.4355, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.47533752675449326, "learning_rate": 3.9859116648464534e-05, "loss": 0.4413, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.4500152591903391, "learning_rate": 3.985233641724152e-05, "loss": 0.4413, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.523169459254909, "learning_rate": 3.984539744726554e-05, "loss": 0.444, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.5109996628758124, "learning_rate": 3.983829979402038e-05, "loss": 0.4483, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.4489199575102444, "learning_rate": 3.983104351425871e-05, "loss": 0.4249, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.5289412754552762, "learning_rate": 3.982362866600154e-05, "loss": 0.4517, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.5248931228941242, "learning_rate": 3.9816055308537806e-05, "loss": 0.4461, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.4522380499434015, "learning_rate": 3.980832350242388e-05, "loss": 0.438, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.49315261124858234, "learning_rate": 3.980043330948306e-05, "loss": 0.4443, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.4571761998750754, "learning_rate": 3.9792384792805124e-05, "loss": 0.4497, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5847576999804488, "learning_rate": 3.978417801674579e-05, "loss": 0.4476, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.5235605397401036, "learning_rate": 3.9775813046926244e-05, "loss": 0.4389, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5051918690645328, "learning_rate": 3.976728995023254e-05, "loss": 0.4337, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.5573944946624182, "learning_rate": 3.975860879481514e-05, "loss": 0.449, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.7318812540946429, "learning_rate": 3.974976965008833e-05, "loss": 0.4284, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5329731628985466, "learning_rate": 3.9740772586729674e-05, "loss": 0.4377, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.44189558496513487, "learning_rate": 3.973161767667946e-05, "loss": 0.4278, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.7787736375133999, "learning_rate": 3.972230499314009e-05, "loss": 0.4508, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.7193828710158146, "learning_rate": 3.9712834610575545e-05, "loss": 0.4528, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.44440738620205456, "learning_rate": 3.9703206604710746e-05, "loss": 0.4385, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.7229712229768622, "learning_rate": 3.969342105253098e-05, "loss": 0.4476, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6656012912160998, "learning_rate": 3.9683478032281246e-05, "loss": 0.4513, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.4893643377568331, "learning_rate": 3.967337762346568e-05, "loss": 0.4234, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.5582282659734965, "learning_rate": 3.9663119906846885e-05, "loss": 0.4441, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.43677019214533735, "learning_rate": 3.965270496444528e-05, "loss": 0.4316, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.47718977880745056, "learning_rate": 3.9642132879538465e-05, "loss": 0.4442, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.4407535383509904, "learning_rate": 3.9631403736660566e-05, "loss": 0.4403, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.4254831495102962, "learning_rate": 3.962051762160151e-05, "loss": 0.4384, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.5210697418792266, "learning_rate": 3.960947462140638e-05, "loss": 0.4546, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5743905830472941, "learning_rate": 3.959827482437472e-05, "loss": 0.4462, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.4417290837132035, "learning_rate": 3.958691832005981e-05, "loss": 0.4357, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.6629980759879784, "learning_rate": 3.9575405199267944e-05, "loss": 0.4462, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.5725812236309967, "learning_rate": 3.956373555405774e-05, "loss": 0.4492, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.46814034046187825, "learning_rate": 3.955190947773937e-05, "loss": 0.4408, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.4729112434764096, "learning_rate": 3.9539927064873824e-05, "loss": 0.4251, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.3613374792122385, "learning_rate": 3.952778841127214e-05, "loss": 0.4376, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.543524034168925, "learning_rate": 3.95154936139947e-05, "loss": 0.4343, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.4804895690564262, "learning_rate": 3.950304277135034e-05, "loss": 0.4341, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.3714329838419394, "learning_rate": 3.94904359828957e-05, "loss": 0.4361, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.48562083940538675, "learning_rate": 3.94776733494343e-05, "loss": 0.4338, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.47117636204090724, "learning_rate": 3.9464754973015826e-05, "loss": 0.4284, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.3756645136126478, "learning_rate": 3.9451680956935275e-05, "loss": 0.437, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5897110573611795, "learning_rate": 3.943845140573213e-05, "loss": 0.4385, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.40864733171458145, "learning_rate": 3.942506642518952e-05, "loss": 0.4085, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.5011996470878741, "learning_rate": 3.9411526122333396e-05, "loss": 0.4278, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.6225939630862097, "learning_rate": 3.939783060543167e-05, "loss": 0.4336, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.4569225215602834, "learning_rate": 3.938397998399333e-05, "loss": 0.4244, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.4427960695827378, "learning_rate": 3.936997436876756e-05, "loss": 0.4357, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.40846225270754843, "learning_rate": 3.935581387174289e-05, "loss": 0.4401, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5279213681223535, "learning_rate": 3.9341498606146295e-05, "loss": 0.4419, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.4490903214771515, "learning_rate": 3.932702868644224e-05, "loss": 0.4378, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.3814941546610759, "learning_rate": 3.931240422833181e-05, "loss": 0.4406, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.3862661452286689, "learning_rate": 3.9297625348751806e-05, "loss": 0.4197, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.3774964125678653, "learning_rate": 3.9282692165873744e-05, "loss": 0.4218, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.39622475713713945, "learning_rate": 3.9267604799102945e-05, "loss": 0.4158, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.4566720545601095, "learning_rate": 3.9252363369077615e-05, "loss": 0.4316, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.39303032778597413, "learning_rate": 3.9236967997667796e-05, "loss": 0.4202, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.44320345577464076, "learning_rate": 3.9221418807974496e-05, "loss": 0.4332, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5300334679756743, "learning_rate": 3.92057159243286e-05, "loss": 0.4353, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.44380580528542096, "learning_rate": 3.9189859472289956e-05, "loss": 0.418, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.3809426417696378, "learning_rate": 3.9173849578646324e-05, "loss": 0.4321, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.48801384607291687, "learning_rate": 3.9157686371412395e-05, "loss": 0.4359, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.46880244350367356, "learning_rate": 3.914136997982874e-05, "loss": 0.441, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5072062433910633, "learning_rate": 3.912490053436079e-05, "loss": 0.4457, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.4956904247418389, "learning_rate": 3.9108278166697805e-05, "loss": 0.4231, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.3812065192614791, "learning_rate": 3.909150300975178e-05, "loss": 0.4212, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.38604595005529724, "learning_rate": 3.907457519765642e-05, "loss": 0.4316, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.43956611327828926, "learning_rate": 3.905749486576607e-05, "loss": 0.4156, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.45611113893190985, "learning_rate": 3.90402621506546e-05, "loss": 0.42, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4410837161362029, "learning_rate": 3.902287719011435e-05, "loss": 0.4306, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.461216251798161, "learning_rate": 3.900534012315499e-05, "loss": 0.4377, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5567880947890924, "learning_rate": 3.8987651090002454e-05, "loss": 0.4365, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.5994193081667372, "learning_rate": 3.896981023209777e-05, "loss": 0.4236, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.5056945304049544, "learning_rate": 3.8951817692095966e-05, "loss": 0.4235, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4256715622879917, "learning_rate": 3.893367361386491e-05, "loss": 0.4248, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4419311407632905, "learning_rate": 3.891537814248417e-05, "loss": 0.4215, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4580622899641616, "learning_rate": 3.889693142424384e-05, "loss": 0.4199, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.4489316027259135, "learning_rate": 3.8878333606643405e-05, "loss": 0.44, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.41740714811802426, "learning_rate": 3.885958483839049e-05, "loss": 0.4249, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.44525334059933874, "learning_rate": 3.8840685269399786e-05, "loss": 0.4217, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.4253544094407922, "learning_rate": 3.882163505079171e-05, "loss": 0.4331, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.43147964438600656, "learning_rate": 3.880243433489132e-05, "loss": 0.4247, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.41103493996775325, "learning_rate": 3.878308327522702e-05, "loss": 0.3991, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.4674181765241295, "learning_rate": 3.876358202652936e-05, "loss": 0.3983, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5052651752606261, "learning_rate": 3.8743930744729835e-05, "loss": 0.3885, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.4154225228850512, "learning_rate": 3.8724129586959535e-05, "loss": 0.4004, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.45439669200622457, "learning_rate": 3.870417871154801e-05, "loss": 0.3959, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.46893086142713963, "learning_rate": 3.868407827802192e-05, "loss": 0.3892, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.38332867898158846, "learning_rate": 3.8663828447103804e-05, "loss": 0.3845, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.5166632045917312, "learning_rate": 3.8643429380710765e-05, "loss": 0.3888, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.4161990511532694, "learning_rate": 3.862288124195319e-05, "loss": 0.399, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.5484368130537997, "learning_rate": 3.8602184195133464e-05, "loss": 0.3859, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.48493941982696376, "learning_rate": 3.8581338405744604e-05, "loss": 0.3797, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.4722441116198641, "learning_rate": 3.8560344040468996e-05, "loss": 0.395, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5708877085791426, "learning_rate": 3.853920126717703e-05, "loss": 0.3914, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.4879498065952958, "learning_rate": 3.851791025492574e-05, "loss": 0.3709, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.5590774256501628, "learning_rate": 3.8496471173957515e-05, "loss": 0.392, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.4419643984844331, "learning_rate": 3.847488419569866e-05, "loss": 0.3969, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.4967386018937095, "learning_rate": 3.8453149492758077e-05, "loss": 0.3935, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.4860325468096205, "learning_rate": 3.8431267238925886e-05, "loss": 0.3813, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.49645975760173916, "learning_rate": 3.840923760917199e-05, "loss": 0.3987, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.46859786395063874, "learning_rate": 3.838706077964473e-05, "loss": 0.3772, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.47013845531713494, "learning_rate": 3.836473692766944e-05, "loss": 0.3977, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5941192246375075, "learning_rate": 3.834226623174705e-05, "loss": 0.3886, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.5099967938046914, "learning_rate": 3.831964887155264e-05, "loss": 0.3878, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.4793912470603942, "learning_rate": 3.829688502793403e-05, "loss": 0.3891, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5354699199539915, "learning_rate": 3.827397488291029e-05, "loss": 0.3857, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.5014638794560451, "learning_rate": 3.8250918619670343e-05, "loss": 0.3993, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.41437888109583493, "learning_rate": 3.822771642257145e-05, "loss": 0.3818, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.461404878906344, "learning_rate": 3.820436847713776e-05, "loss": 0.379, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.42880255535745665, "learning_rate": 3.8180874970058826e-05, "loss": 0.3816, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.3907471765600839, "learning_rate": 3.8157236089188103e-05, "loss": 0.3985, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.47137450920955426, "learning_rate": 3.813345202354145e-05, "loss": 0.3797, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.3918293265261156, "learning_rate": 3.810952296329563e-05, "loss": 0.3935, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.4488721807573471, "learning_rate": 3.808544909978676e-05, "loss": 0.3873, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.4097334119986228, "learning_rate": 3.806123062550882e-05, "loss": 0.3884, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.4111196674420365, "learning_rate": 3.803686773411208e-05, "loss": 0.396, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.3859203379997195, "learning_rate": 3.801236062040158e-05, "loss": 0.3858, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.33763047470592955, "learning_rate": 3.798770948033553e-05, "loss": 0.382, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.40598834851724624, "learning_rate": 3.796291451102381e-05, "loss": 0.3833, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.41695203784229734, "learning_rate": 3.793797591072631e-05, "loss": 0.3795, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.31490725884257964, "learning_rate": 3.791289387885144e-05, "loss": 0.3811, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.3955777633738354, "learning_rate": 3.788766861595443e-05, "loss": 0.389, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.4428865256198812, "learning_rate": 3.7862300323735835e-05, "loss": 0.3831, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.46313246888550624, "learning_rate": 3.783678920503983e-05, "loss": 0.3844, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.37957057177238973, "learning_rate": 3.781113546385265e-05, "loss": 0.3928, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.3768917928794411, "learning_rate": 3.7785339305300916e-05, "loss": 0.3996, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.49437902772406794, "learning_rate": 3.7759400935650025e-05, "loss": 0.3835, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.4170452726860274, "learning_rate": 3.77333205623025e-05, "loss": 0.3837, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.3831012871479016, "learning_rate": 3.7707098393796295e-05, "loss": 0.3829, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.3908675519145198, "learning_rate": 3.7680734639803185e-05, "loss": 0.3937, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.3967264105740338, "learning_rate": 3.765422951112704e-05, "loss": 0.3978, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.48089983542667003, "learning_rate": 3.762758321970216e-05, "loss": 0.3841, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.440618820856736, "learning_rate": 3.7600795978591584e-05, "loss": 0.3953, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.38925392205148046, "learning_rate": 3.757386800198538e-05, "loss": 0.3903, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.3838735617522689, "learning_rate": 3.7546799505198925e-05, "loss": 0.3868, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.4033815928908875, "learning_rate": 3.7519590704671197e-05, "loss": 0.3949, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4014230025651636, "learning_rate": 3.749224181796305e-05, "loss": 0.3909, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.3202955169151333, "learning_rate": 3.746475306375545e-05, "loss": 0.3888, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.3914607367019438, "learning_rate": 3.743712466184774e-05, "loss": 0.3818, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.3223472521219414, "learning_rate": 3.7409356833155885e-05, "loss": 0.3871, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.37049526552194606, "learning_rate": 3.73814497997107e-05, "loss": 0.3919, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.36447517393432616, "learning_rate": 3.7353403784656095e-05, "loss": 0.3876, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.39087437233318134, "learning_rate": 3.732521901224724e-05, "loss": 0.3775, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.43805246056410785, "learning_rate": 3.7296895707848844e-05, "loss": 0.395, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.3803002990921762, "learning_rate": 3.7268434097933275e-05, "loss": 0.377, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.4156626392405206, "learning_rate": 3.723983441007882e-05, "loss": 0.3902, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.3533564146523915, "learning_rate": 3.721109687296781e-05, "loss": 0.3869, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.3761791503659039, "learning_rate": 3.718222171638484e-05, "loss": 0.3808, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.45612238918858233, "learning_rate": 3.715320917121488e-05, "loss": 0.3767, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.39497548167064384, "learning_rate": 3.712405946944149e-05, "loss": 0.3939, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.48170310725516724, "learning_rate": 3.709477284414488e-05, "loss": 0.3918, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.43974250274133425, "learning_rate": 3.7065349529500136e-05, "loss": 0.3789, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.3879155293802309, "learning_rate": 3.7035789760775305e-05, "loss": 0.3818, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.39702255557541716, "learning_rate": 3.70060937743295e-05, "loss": 0.3934, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.3900371938383351, "learning_rate": 3.6976261807611045e-05, "loss": 0.3887, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.36102070814386344, "learning_rate": 3.694629409915555e-05, "loss": 0.3833, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4533123835446057, "learning_rate": 3.691619088858401e-05, "loss": 0.4061, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.4350411574821708, "learning_rate": 3.68859524166009e-05, "loss": 0.3889, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.41200684169948304, "learning_rate": 3.6855578924992226e-05, "loss": 0.3803, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.35567920601196157, "learning_rate": 3.6825070656623626e-05, "loss": 0.383, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.41539056005721253, "learning_rate": 3.67944278554384e-05, "loss": 0.3929, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.45508799691062835, "learning_rate": 3.676365076645557e-05, "loss": 0.3852, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.35459515020583976, "learning_rate": 3.673273963576791e-05, "loss": 0.3807, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.3988642488658846, "learning_rate": 3.670169471054001e-05, "loss": 0.3912, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.4096944893050068, "learning_rate": 3.6670516239006254e-05, "loss": 0.3831, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.33611676339054397, "learning_rate": 3.663920447046888e-05, "loss": 0.3828, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.40104136884857927, "learning_rate": 3.6607759655295954e-05, "loss": 0.3827, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.34190799659917254, "learning_rate": 3.657618204491937e-05, "loss": 0.3885, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.36795255758560874, "learning_rate": 3.6544471891832875e-05, "loss": 0.3898, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.33786565883881653, "learning_rate": 3.6512629449589983e-05, "loss": 0.3801, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.3661099516958216, "learning_rate": 3.6480654972802045e-05, "loss": 0.3935, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.39869679232068606, "learning_rate": 3.644854871713611e-05, "loss": 0.3961, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.349967763029176, "learning_rate": 3.6416310939312924e-05, "loss": 0.3854, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.3246846010857422, "learning_rate": 3.638394189710493e-05, "loss": 0.3824, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.34697949898789215, "learning_rate": 3.635144184933412e-05, "loss": 0.3855, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.33728908522553097, "learning_rate": 3.6318811055869994e-05, "loss": 0.3994, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.39193998824066156, "learning_rate": 3.628604977762752e-05, "loss": 0.3763, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.417159156126333, "learning_rate": 3.6253158276565004e-05, "loss": 0.4067, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.32816562120308845, "learning_rate": 3.6220136815682016e-05, "loss": 0.3812, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.38528822134592544, "learning_rate": 3.618698565901727e-05, "loss": 0.3835, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.3541579972192127, "learning_rate": 3.615370507164654e-05, "loss": 0.384, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.37530553972738867, "learning_rate": 3.61202953196805e-05, "loss": 0.3893, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.3491665160633737, "learning_rate": 3.6086756670262654e-05, "loss": 0.3757, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4066213849882577, "learning_rate": 3.6053089391567135e-05, "loss": 0.3724, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.41338586454380916, "learning_rate": 3.601929375279662e-05, "loss": 0.3931, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.3484810234614011, "learning_rate": 3.598537002418012e-05, "loss": 0.397, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.34862017276585267, "learning_rate": 3.5951318476970885e-05, "loss": 0.3938, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.3218780791870411, "learning_rate": 3.591713938344416e-05, "loss": 0.3944, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.38066004610545207, "learning_rate": 3.588283301689507e-05, "loss": 0.3887, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.33710896000019114, "learning_rate": 3.5848399651636424e-05, "loss": 0.3833, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.3902050421930115, "learning_rate": 3.5813839562996473e-05, "loss": 0.3742, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.33585305847839775, "learning_rate": 3.5779153027316775e-05, "loss": 0.3852, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.3440314414550614, "learning_rate": 3.574434032194994e-05, "loss": 0.3815, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.3569815701433396, "learning_rate": 3.5709401725257436e-05, "loss": 0.3817, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.32592946732620204, "learning_rate": 3.5674337516607346e-05, "loss": 0.3762, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.3337742681679686, "learning_rate": 3.563914797637216e-05, "loss": 0.3767, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.32696365593356697, "learning_rate": 3.560383338592649e-05, "loss": 0.3857, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.3723559423954499, "learning_rate": 3.556839402764487e-05, "loss": 0.376, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.323762956303158, "learning_rate": 3.553283018489946e-05, "loss": 0.3762, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.3712883261480001, "learning_rate": 3.54971421420578e-05, "loss": 0.3803, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.3981542270961483, "learning_rate": 3.5461330184480524e-05, "loss": 0.3788, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.467736487087826, "learning_rate": 3.54253945985191e-05, "loss": 0.3943, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4208136950955791, "learning_rate": 3.5389335671513524e-05, "loss": 0.365, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.47216171736759915, "learning_rate": 3.5353153691789986e-05, "loss": 0.3806, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.37840898301518777, "learning_rate": 3.531684894865866e-05, "loss": 0.3863, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.3770730501149013, "learning_rate": 3.528042173241128e-05, "loss": 0.3751, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.42703910611910667, "learning_rate": 3.524387233431892e-05, "loss": 0.3662, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.37483479554821614, "learning_rate": 3.520720104662958e-05, "loss": 0.3786, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.5540106660827063, "learning_rate": 3.5170408162565904e-05, "loss": 0.3999, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.4654284925805928, "learning_rate": 3.513349397632281e-05, "loss": 0.3892, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4590270119590404, "learning_rate": 3.5096458783065145e-05, "loss": 0.388, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5022413802712529, "learning_rate": 3.505930287892533e-05, "loss": 0.3733, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.5094525506769736, "learning_rate": 3.502202656100099e-05, "loss": 0.3829, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5553768214010231, "learning_rate": 3.498463012735256e-05, "loss": 0.4037, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.44963288381344085, "learning_rate": 3.494711387700094e-05, "loss": 0.3825, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.5302397134078457, "learning_rate": 3.490947810992505e-05, "loss": 0.3889, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.623079934579586, "learning_rate": 3.48717231270595e-05, "loss": 0.3878, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4244152464304998, "learning_rate": 3.483384923029211e-05, "loss": 0.3795, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.5848454316808356, "learning_rate": 3.479585672246156e-05, "loss": 0.383, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.48289432402297805, "learning_rate": 3.4757745907354924e-05, "loss": 0.3737, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4343476621879905, "learning_rate": 3.471951708970527e-05, "loss": 0.3896, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4781649518277526, "learning_rate": 3.468117057518921e-05, "loss": 0.3918, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.3630713799321207, "learning_rate": 3.4642706670424426e-05, "loss": 0.3876, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.4147243436460151, "learning_rate": 3.460412568296731e-05, "loss": 0.3811, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.3752189162411106, "learning_rate": 3.456542792131039e-05, "loss": 0.3773, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.41816790996237213, "learning_rate": 3.4526613694879936e-05, "loss": 0.3841, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.37088669210324726, "learning_rate": 3.448768331403348e-05, "loss": 0.392, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.5013762339732962, "learning_rate": 3.44486370900573e-05, "loss": 0.3724, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.4659452895581128, "learning_rate": 3.440947533516396e-05, "loss": 0.3907, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.46212120615513347, "learning_rate": 3.4370198362489816e-05, "loss": 0.3692, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.49666024454622004, "learning_rate": 3.43308064860925e-05, "loss": 0.3896, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.41077250899006273, "learning_rate": 3.4291300020948393e-05, "loss": 0.3762, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.36515640164310154, "learning_rate": 3.425167928295015e-05, "loss": 0.3836, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.43349565533025636, "learning_rate": 3.421194458890411e-05, "loss": 0.3751, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.3313637883079575, "learning_rate": 3.4172096256527865e-05, "loss": 0.3765, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.37725193433615534, "learning_rate": 3.4132134604447595e-05, "loss": 0.3873, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.3537208573672572, "learning_rate": 3.409205995219561e-05, "loss": 0.3855, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.41817308196616737, "learning_rate": 3.4051872620207765e-05, "loss": 0.3625, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.34833821440881907, "learning_rate": 3.40115729298209e-05, "loss": 0.3858, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.37221462153130336, "learning_rate": 3.397116120327025e-05, "loss": 0.3815, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.3688011814803626, "learning_rate": 3.3930637763686916e-05, "loss": 0.3826, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.36309743622283375, "learning_rate": 3.389000293509524e-05, "loss": 0.3678, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.2788924517187729, "learning_rate": 3.3849257042410225e-05, "loss": 0.3793, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.379778281181601, "learning_rate": 3.380840041143494e-05, "loss": 0.3815, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.31987603839670753, "learning_rate": 3.376743336885792e-05, "loss": 0.3691, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.34556649623334623, "learning_rate": 3.372635624225055e-05, "loss": 0.3812, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.37190367473347297, "learning_rate": 3.3685169360064445e-05, "loss": 0.3777, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.339689736148055, "learning_rate": 3.3643873051628804e-05, "loss": 0.377, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.3379602288129871, "learning_rate": 3.3602467647147814e-05, "loss": 0.4026, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.3646866173740445, "learning_rate": 3.356095347769799e-05, "loss": 0.3881, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.3531925655737405, "learning_rate": 3.351933087522552e-05, "loss": 0.3696, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.3190996059326977, "learning_rate": 3.3477600172543626e-05, "loss": 0.3813, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.37091092585660956, "learning_rate": 3.3435761703329894e-05, "loss": 0.3803, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.3695834082885275, "learning_rate": 3.3393815802123606e-05, "loss": 0.373, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.3043023678856067, "learning_rate": 3.335176280432308e-05, "loss": 0.3729, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.3959233317501943, "learning_rate": 3.330960304618295e-05, "loss": 0.3872, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.3885981539823375, "learning_rate": 3.326733686481153e-05, "loss": 0.3935, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.36504672155526957, "learning_rate": 3.3224964598168084e-05, "loss": 0.3903, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.4215835495176867, "learning_rate": 3.318248658506012e-05, "loss": 0.3751, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.45164349046867036, "learning_rate": 3.313990316514069e-05, "loss": 0.3705, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.3580465140491445, "learning_rate": 3.309721467890571e-05, "loss": 0.3791, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.405362062049195, "learning_rate": 3.305442146769115e-05, "loss": 0.3594, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.30694255763676115, "learning_rate": 3.30115238736704e-05, "loss": 0.3758, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.41572667065669383, "learning_rate": 3.296852223985148e-05, "loss": 0.3751, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3183478352178612, "learning_rate": 3.2925416910074315e-05, "loss": 0.3774, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.3379732156525689, "learning_rate": 3.288220822900796e-05, "loss": 0.3738, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.3263339739367207, "learning_rate": 3.283889654214788e-05, "loss": 0.3899, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.2836309062042586, "learning_rate": 3.279548219581317e-05, "loss": 0.3697, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.30482859767811926, "learning_rate": 3.275196553714379e-05, "loss": 0.377, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.32656477439375614, "learning_rate": 3.270834691409778e-05, "loss": 0.384, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.3055464409652836, "learning_rate": 3.266462667544849e-05, "loss": 0.3822, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.3745248539094569, "learning_rate": 3.262080517078178e-05, "loss": 0.3885, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.30778327360174945, "learning_rate": 3.257688275049323e-05, "loss": 0.3701, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.3730796654373569, "learning_rate": 3.253285976578535e-05, "loss": 0.3788, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.2786036383968664, "learning_rate": 3.2488736568664756e-05, "loss": 0.3802, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.3216850100125628, "learning_rate": 3.244451351193935e-05, "loss": 0.3752, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.2923784194627644, "learning_rate": 3.240019094921551e-05, "loss": 0.3679, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.26719441183788717, "learning_rate": 3.235576923489527e-05, "loss": 0.393, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.3075513380149316, "learning_rate": 3.2311248724173476e-05, "loss": 0.3963, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.31063723690679446, "learning_rate": 3.226662977303494e-05, "loss": 0.3817, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.29940143601746666, "learning_rate": 3.2221912738251626e-05, "loss": 0.3775, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.33056638217898393, "learning_rate": 3.2177097977379736e-05, "loss": 0.3866, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.39686660410252794, "learning_rate": 3.21321858487569e-05, "loss": 0.3734, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.3351134733412476, "learning_rate": 3.208717671149931e-05, "loss": 0.3863, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.3960222766735387, "learning_rate": 3.204207092549882e-05, "loss": 0.3741, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.3669433355041008, "learning_rate": 3.19968688514201e-05, "loss": 0.3954, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.46651048630401, "learning_rate": 3.195157085069774e-05, "loss": 0.3921, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.29199607822227247, "learning_rate": 3.190617728553332e-05, "loss": 0.3617, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.35052267502386014, "learning_rate": 3.1860688518892606e-05, "loss": 0.3683, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.3591145438682825, "learning_rate": 3.181510491450254e-05, "loss": 0.3933, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.3431227569574978, "learning_rate": 3.176942683684842e-05, "loss": 0.3685, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.31015890332694224, "learning_rate": 3.1723654651170934e-05, "loss": 0.3857, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.34688094545928266, "learning_rate": 3.167778872346327e-05, "loss": 0.3804, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.3179496394754672, "learning_rate": 3.163182942046815e-05, "loss": 0.3685, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.33132596204037074, "learning_rate": 3.158577710967494e-05, "loss": 0.3725, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.2890464131822429, "learning_rate": 3.153963215931669e-05, "loss": 0.3782, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.36139820136970574, "learning_rate": 3.14933949383672e-05, "loss": 0.3734, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.2967589467008387, "learning_rate": 3.144706581653805e-05, "loss": 0.3857, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.34199155559859834, "learning_rate": 3.140064516427566e-05, "loss": 0.3742, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.30084667131278015, "learning_rate": 3.135413335275833e-05, "loss": 0.3711, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.3503929370906648, "learning_rate": 3.130753075389327e-05, "loss": 0.3746, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.3350109494213542, "learning_rate": 3.1260837740313625e-05, "loss": 0.3886, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.31722763672542315, "learning_rate": 3.121405468537547e-05, "loss": 0.3669, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.32263139139299374, "learning_rate": 3.116718196315488e-05, "loss": 0.3714, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.3077067730817458, "learning_rate": 3.1120219948444894e-05, "loss": 0.3796, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.31314033862968593, "learning_rate": 3.107316901675252e-05, "loss": 0.3739, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.33332546441243194, "learning_rate": 3.1026029544295745e-05, "loss": 0.381, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.28973330879711107, "learning_rate": 3.097880190800057e-05, "loss": 0.3781, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3394100885791649, "learning_rate": 3.093148648549788e-05, "loss": 0.377, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.2851449082328533, "learning_rate": 3.088408365512055e-05, "loss": 0.3797, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.28863097821439915, "learning_rate": 3.083659379590034e-05, "loss": 0.3866, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.2775378699127375, "learning_rate": 3.0789017287564913e-05, "loss": 0.3735, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.32908347031432805, "learning_rate": 3.074135451053475e-05, "loss": 0.3735, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.26475237948738706, "learning_rate": 3.069360584592015e-05, "loss": 0.3623, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.34248478120410436, "learning_rate": 3.064577167551816e-05, "loss": 0.3551, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.3361392827530124, "learning_rate": 3.059785238180953e-05, "loss": 0.3844, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.32406723221247047, "learning_rate": 3.054984834795566e-05, "loss": 0.3798, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.3065642859674465, "learning_rate": 3.0501759957795537e-05, "loss": 0.3788, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.3187277610170312, "learning_rate": 3.0453587595842627e-05, "loss": 0.3751, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.2895205364288924, "learning_rate": 3.0405331647281856e-05, "loss": 0.3852, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.35554285168435357, "learning_rate": 3.0356992497966508e-05, "loss": 0.3701, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.29110442297952516, "learning_rate": 3.0308570534415137e-05, "loss": 0.3821, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.27809649447802676, "learning_rate": 3.0260066143808467e-05, "loss": 0.362, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.28679245261810865, "learning_rate": 3.021147971398632e-05, "loss": 0.3675, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.27802154703258625, "learning_rate": 3.0162811633444478e-05, "loss": 0.3839, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.29412589647667775, "learning_rate": 3.0114062291331635e-05, "loss": 0.3709, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.29361331400849827, "learning_rate": 3.0065232077446217e-05, "loss": 0.3679, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.25350112511093276, "learning_rate": 3.001632138223332e-05, "loss": 0.3688, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.4196043923125445, "learning_rate": 2.9967330596781565e-05, "loss": 0.3369, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 1.0295862391881538, "learning_rate": 2.9918260112819952e-05, "loss": 0.3355, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5432570080497796, "learning_rate": 2.9869110322714778e-05, "loss": 0.3184, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.3614246365190228, "learning_rate": 2.9819881619466447e-05, "loss": 0.3203, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.3996543449762488, "learning_rate": 2.9770574396706364e-05, "loss": 0.3264, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5094322425565178, "learning_rate": 2.972118904869376e-05, "loss": 0.3325, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.5510120653355698, "learning_rate": 2.9671725970312563e-05, "loss": 0.3139, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5468038322514267, "learning_rate": 2.9622185557068238e-05, "loss": 0.3308, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.43378075758200174, "learning_rate": 2.95725682050846e-05, "loss": 0.3297, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.47648013209148304, "learning_rate": 2.9522874311100684e-05, "loss": 0.3196, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.43897270119849446, "learning_rate": 2.9473104272467526e-05, "loss": 0.3229, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4094265581374034, "learning_rate": 2.942325848714505e-05, "loss": 0.3296, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.4783578959187047, "learning_rate": 2.9373337353698804e-05, "loss": 0.3301, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.3309172934644, "learning_rate": 2.932334127129686e-05, "loss": 0.3256, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.3603546206283281, "learning_rate": 2.9273270639706547e-05, "loss": 0.3179, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.3874318001626755, "learning_rate": 2.922312585929131e-05, "loss": 0.3279, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.3843260175892144, "learning_rate": 2.9172907331007478e-05, "loss": 0.3231, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.29523183700541233, "learning_rate": 2.9122615456401053e-05, "loss": 0.3168, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.37629615527773586, "learning_rate": 2.9072250637604535e-05, "loss": 0.3229, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.31300631450253924, "learning_rate": 2.9021813277333667e-05, "loss": 0.3172, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.3906309341447702, "learning_rate": 2.8971303778884244e-05, "loss": 0.3195, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.2983453966768671, "learning_rate": 2.8920722546128863e-05, "loss": 0.3233, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.3944459956324581, "learning_rate": 2.887006998351372e-05, "loss": 0.3236, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.33399365673747333, "learning_rate": 2.881934649605535e-05, "loss": 0.3203, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.3729466762464218, "learning_rate": 2.8768552489337408e-05, "loss": 0.3384, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.35699679132358414, "learning_rate": 2.8717688369507425e-05, "loss": 0.3313, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.35949757630602397, "learning_rate": 2.8666754543273535e-05, "loss": 0.3123, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.31963805983357624, "learning_rate": 2.8615751417901273e-05, "loss": 0.3135, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.31841657737542767, "learning_rate": 2.856467940121025e-05, "loss": 0.3278, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.31587036914789685, "learning_rate": 2.8513538901570964e-05, "loss": 0.3157, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.2629171193540334, "learning_rate": 2.846233032790149e-05, "loss": 0.319, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.30310673498004, "learning_rate": 2.84110540896642e-05, "loss": 0.3229, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.2986475133649132, "learning_rate": 2.8359710596862555e-05, "loss": 0.3108, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.274416896164463, "learning_rate": 2.8308300260037734e-05, "loss": 0.3145, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.32516442669796347, "learning_rate": 2.8256823490265424e-05, "loss": 0.3143, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3508979332645743, "learning_rate": 2.8205280699152515e-05, "loss": 0.3282, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.281153546520247, "learning_rate": 2.8153672298833777e-05, "loss": 0.3282, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3410304132786259, "learning_rate": 2.8101998701968615e-05, "loss": 0.3308, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.30575747915550205, "learning_rate": 2.805026032173773e-05, "loss": 0.3187, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.2980261277397434, "learning_rate": 2.7998457571839832e-05, "loss": 0.3354, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.30067992534355253, "learning_rate": 2.7946590866488322e-05, "loss": 0.3273, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.31000229185904016, "learning_rate": 2.7894660620408e-05, "loss": 0.3142, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.30149211259605135, "learning_rate": 2.784266724883173e-05, "loss": 0.3229, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3004911554023862, "learning_rate": 2.7790611167497128e-05, "loss": 0.3168, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3306711174167467, "learning_rate": 2.7738492792643224e-05, "loss": 0.324, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3090217865473803, "learning_rate": 2.768631254100716e-05, "loss": 0.3218, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.29552444027023606, "learning_rate": 2.7634070829820836e-05, "loss": 0.3226, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.2819448586876796, "learning_rate": 2.7581768076807592e-05, "loss": 0.3201, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.2817305071495267, "learning_rate": 2.7529404700178832e-05, "loss": 0.3302, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.29275822368031423, "learning_rate": 2.7476981118630735e-05, "loss": 0.333, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.30018362580130853, "learning_rate": 2.742449775134085e-05, "loss": 0.3062, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.3219746080273496, "learning_rate": 2.7371955017964788e-05, "loss": 0.3206, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.30508754491218276, "learning_rate": 2.7319353338632845e-05, "loss": 0.3131, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3267934467536459, "learning_rate": 2.7266693133946645e-05, "loss": 0.3216, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.30755652493196284, "learning_rate": 2.7213974824975785e-05, "loss": 0.3193, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3593202903336603, "learning_rate": 2.7161198833254464e-05, "loss": 0.3155, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.36907518884111207, "learning_rate": 2.7108365580778095e-05, "loss": 0.3273, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3220354508827021, "learning_rate": 2.705547548999996e-05, "loss": 0.3316, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.3314945837561245, "learning_rate": 2.7002528983827817e-05, "loss": 0.3337, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3166017301674852, "learning_rate": 2.6949526485620517e-05, "loss": 0.3265, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.30937582669658453, "learning_rate": 2.6896468419184623e-05, "loss": 0.335, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.3260762035712931, "learning_rate": 2.6843355208771024e-05, "loss": 0.3154, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3709894525238288, "learning_rate": 2.6790187279071536e-05, "loss": 0.3238, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.3144346014180377, "learning_rate": 2.67369650552155e-05, "loss": 0.3243, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.3413562284117849, "learning_rate": 2.6683688962766407e-05, "loss": 0.3285, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.2580927165913988, "learning_rate": 2.6630359427718468e-05, "loss": 0.3065, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.33076809309220384, "learning_rate": 2.6576976876493225e-05, "loss": 0.3182, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.2961731845618526, "learning_rate": 2.652354173593614e-05, "loss": 0.3305, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.34325238406270825, "learning_rate": 2.647005443331317e-05, "loss": 0.3326, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3180988260822038, "learning_rate": 2.6416515396307354e-05, "loss": 0.3343, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.30774227835445067, "learning_rate": 2.636292505301542e-05, "loss": 0.3335, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3265022821963238, "learning_rate": 2.630928383194431e-05, "loss": 0.3177, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.2856430783467796, "learning_rate": 2.625559216200781e-05, "loss": 0.3229, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.33613959946695254, "learning_rate": 2.620185047252308e-05, "loss": 0.3281, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.3097352159359252, "learning_rate": 2.614805919320723e-05, "loss": 0.3355, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.2978204184752973, "learning_rate": 2.6094218754173895e-05, "loss": 0.3309, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.29010528038252414, "learning_rate": 2.60403295859298e-05, "loss": 0.3272, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3065391557778211, "learning_rate": 2.5986392119371297e-05, "loss": 0.3267, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.2979475738182362, "learning_rate": 2.5932406785780928e-05, "loss": 0.3305, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.28359882957778504, "learning_rate": 2.5878374016823987e-05, "loss": 0.3297, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.2938922762840449, "learning_rate": 2.5824294244545045e-05, "loss": 0.332, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.2783673195046346, "learning_rate": 2.577016790136453e-05, "loss": 0.3245, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.2996363051001136, "learning_rate": 2.5715995420075225e-05, "loss": 0.3416, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.2697023308642455, "learning_rate": 2.5661777233838864e-05, "loss": 0.341, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.2606206765785292, "learning_rate": 2.5607513776182616e-05, "loss": 0.3293, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.2736208211971638, "learning_rate": 2.5553205480995633e-05, "loss": 0.3398, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.2555424929241569, "learning_rate": 2.5498852782525604e-05, "loss": 0.3188, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.2583178213425943, "learning_rate": 2.5444456115375252e-05, "loss": 0.3248, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.27311835148455726, "learning_rate": 2.539001591449889e-05, "loss": 0.3178, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.2773913751154144, "learning_rate": 2.53355326151989e-05, "loss": 0.3251, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.24859907366072134, "learning_rate": 2.5281006653122288e-05, "loss": 0.3303, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.24811885268362815, "learning_rate": 2.5226438464257217e-05, "loss": 0.3202, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.27609477993266685, "learning_rate": 2.5171828484929447e-05, "loss": 0.3281, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.27859694472936586, "learning_rate": 2.5117177151798934e-05, "loss": 0.3245, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.2647893610173051, "learning_rate": 2.506248490185627e-05, "loss": 0.3241, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.2764699441106061, "learning_rate": 2.500775217241923e-05, "loss": 0.3352, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3403160796973919, "learning_rate": 2.4952979401129266e-05, "loss": 0.3171, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.23391244682815882, "learning_rate": 2.4898167025948e-05, "loss": 0.3324, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.2802883473671514, "learning_rate": 2.4843315485153703e-05, "loss": 0.3276, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.25742258128655854, "learning_rate": 2.4788425217337856e-05, "loss": 0.3196, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.26559302308788124, "learning_rate": 2.4733496661401572e-05, "loss": 0.3288, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.27772979865406977, "learning_rate": 2.4678530256552114e-05, "loss": 0.3345, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.2585404988534544, "learning_rate": 2.46235264422994e-05, "loss": 0.3261, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.2893656566156073, "learning_rate": 2.4568485658452452e-05, "loss": 0.3308, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.24384682611888553, "learning_rate": 2.451340834511592e-05, "loss": 0.3299, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.25334809298577493, "learning_rate": 2.4458294942686528e-05, "loss": 0.3225, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.26667358527869456, "learning_rate": 2.440314589184958e-05, "loss": 0.3364, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.31401647187606097, "learning_rate": 2.434796163357541e-05, "loss": 0.3382, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.31615162153654713, "learning_rate": 2.429274260911588e-05, "loss": 0.3203, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.2756978188201525, "learning_rate": 2.423748926000084e-05, "loss": 0.3188, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.29459361517298566, "learning_rate": 2.418220202803459e-05, "loss": 0.3248, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3125342274639554, "learning_rate": 2.412688135529237e-05, "loss": 0.3005, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.254782387955767, "learning_rate": 2.4071527684116807e-05, "loss": 0.3211, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.32395187245796503, "learning_rate": 2.4016141457114372e-05, "loss": 0.323, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.22918223846637062, "learning_rate": 2.396072311715187e-05, "loss": 0.3234, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.32545987340467264, "learning_rate": 2.3905273107352863e-05, "loss": 0.3102, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.2607794525967693, "learning_rate": 2.3849791871094157e-05, "loss": 0.3272, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.28259132226417993, "learning_rate": 2.379427985200223e-05, "loss": 0.3157, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.29221901298284636, "learning_rate": 2.373873749394972e-05, "loss": 0.3165, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.26774312001549333, "learning_rate": 2.3683165241051836e-05, "loss": 0.3283, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.3582539443404996, "learning_rate": 2.3627563537662823e-05, "loss": 0.3432, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.24322762586151542, "learning_rate": 2.3571932828372433e-05, "loss": 0.3258, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.30949465406148413, "learning_rate": 2.351627355800233e-05, "loss": 0.3267, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.2619719736673926, "learning_rate": 2.346058617160256e-05, "loss": 0.316, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.2804886614111218, "learning_rate": 2.3404871114447976e-05, "loss": 0.3215, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.2813052269379686, "learning_rate": 2.334912883203469e-05, "loss": 0.3268, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.30281597120070086, "learning_rate": 2.3293359770076505e-05, "loss": 0.3265, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.2854211815551201, "learning_rate": 2.323756437450136e-05, "loss": 0.3279, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.26467642053412127, "learning_rate": 2.3181743091447754e-05, "loss": 0.3328, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.32153518921443763, "learning_rate": 2.3125896367261164e-05, "loss": 0.3245, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.2837968299786278, "learning_rate": 2.307002464849052e-05, "loss": 0.3186, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.25608443328223485, "learning_rate": 2.30141283818846e-05, "loss": 0.3071, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.26930216580301836, "learning_rate": 2.2958208014388462e-05, "loss": 0.3316, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.25328260319996654, "learning_rate": 2.2902263993139857e-05, "loss": 0.3159, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.266817747310202, "learning_rate": 2.2846296765465708e-05, "loss": 0.3094, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.2589141594077741, "learning_rate": 2.2790306778878465e-05, "loss": 0.3307, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.2691044294254903, "learning_rate": 2.273429448107257e-05, "loss": 0.3208, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.2657360341810834, "learning_rate": 2.2678260319920868e-05, "loss": 0.3321, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.2896777231742931, "learning_rate": 2.262220474347102e-05, "loss": 0.3206, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.25911466161929364, "learning_rate": 2.2566128199941918e-05, "loss": 0.3262, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.27615443617404845, "learning_rate": 2.2510031137720104e-05, "loss": 0.3207, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.24390051954717987, "learning_rate": 2.2453914005356206e-05, "loss": 0.3184, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.25378568581813726, "learning_rate": 2.2397777251561302e-05, "loss": 0.3266, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.26607243286738896, "learning_rate": 2.2341621325203393e-05, "loss": 0.3292, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.2526422156158874, "learning_rate": 2.2285446675303764e-05, "loss": 0.3193, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.27079717714964024, "learning_rate": 2.2229253751033423e-05, "loss": 0.3218, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.23966316817600053, "learning_rate": 2.2173043001709492e-05, "loss": 0.325, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.25870856429496625, "learning_rate": 2.2116814876791627e-05, "loss": 0.3236, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.26939668530486766, "learning_rate": 2.2060569825878413e-05, "loss": 0.3157, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.2516698117357437, "learning_rate": 2.2004308298703777e-05, "loss": 0.3162, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.2768285923655777, "learning_rate": 2.1948030745133396e-05, "loss": 0.3263, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.2600532882307427, "learning_rate": 2.1891737615161083e-05, "loss": 0.3246, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.27602638681334396, "learning_rate": 2.1835429358905218e-05, "loss": 0.3332, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.2490406100761019, "learning_rate": 2.17791064266051e-05, "loss": 0.3325, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.2618574474716227, "learning_rate": 2.172276926861741e-05, "loss": 0.3371, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.2641464094737327, "learning_rate": 2.166641833541255e-05, "loss": 0.3225, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.27445306588706125, "learning_rate": 2.161005407757109e-05, "loss": 0.3204, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.26681823576826214, "learning_rate": 2.155367694578013e-05, "loss": 0.3217, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.2825674925279897, "learning_rate": 2.1497287390829712e-05, "loss": 0.3268, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.25183658743328013, "learning_rate": 2.1440885863609208e-05, "loss": 0.3359, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.25311365362213184, "learning_rate": 2.1384472815103737e-05, "loss": 0.3291, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.2505047885936676, "learning_rate": 2.1328048696390534e-05, "loss": 0.3134, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.28959438093920326, "learning_rate": 2.1271613958635342e-05, "loss": 0.3278, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.23144096179728937, "learning_rate": 2.1215169053088825e-05, "loss": 0.3328, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.32802891159178427, "learning_rate": 2.1158714431082937e-05, "loss": 0.3119, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.2607984299794908, "learning_rate": 2.110225054402733e-05, "loss": 0.3159, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.31948752580190853, "learning_rate": 2.1045777843405747e-05, "loss": 0.318, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.2732669257105454, "learning_rate": 2.09892967807724e-05, "loss": 0.3257, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.2820153031544146, "learning_rate": 2.093280780774835e-05, "loss": 0.3174, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.24735298573693423, "learning_rate": 2.087631137601793e-05, "loss": 0.3303, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.23626907994265905, "learning_rate": 2.0819807937325104e-05, "loss": 0.3147, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.24375926307140383, "learning_rate": 2.0763297943469847e-05, "loss": 0.3134, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.260027540409687, "learning_rate": 2.070678184630458e-05, "loss": 0.3158, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.26259006726740114, "learning_rate": 2.06502600977305e-05, "loss": 0.3162, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.269933648372273, "learning_rate": 2.0593733149694008e-05, "loss": 0.3253, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.2563642086789556, "learning_rate": 2.0537201454183074e-05, "loss": 0.3235, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.29052317369606595, "learning_rate": 2.0480665463223626e-05, "loss": 0.3207, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.24491917931637228, "learning_rate": 2.042412562887594e-05, "loss": 0.3144, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.27386605742693937, "learning_rate": 2.0367582403231033e-05, "loss": 0.3284, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.25874829558151247, "learning_rate": 2.0311036238407023e-05, "loss": 0.327, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.29551728839120084, "learning_rate": 2.0254487586545534e-05, "loss": 0.3318, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.25287832451426695, "learning_rate": 2.0197936899808088e-05, "loss": 0.3152, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.26757333224309043, "learning_rate": 2.0141384630372466e-05, "loss": 0.3204, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.2597102750557314, "learning_rate": 2.0084831230429106e-05, "loss": 0.3365, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.293534800120809, "learning_rate": 2.0028277152177492e-05, "loss": 0.3352, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.2374792086236814, "learning_rate": 1.9971722847822518e-05, "loss": 0.3211, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.2749499740126531, "learning_rate": 1.99151687695709e-05, "loss": 0.3385, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2606474817571971, "learning_rate": 1.9858615369627537e-05, "loss": 0.3223, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.2366894124791772, "learning_rate": 1.9802063100191916e-05, "loss": 0.3211, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.2536075819942685, "learning_rate": 1.974551241345447e-05, "loss": 0.3111, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.24185087001690142, "learning_rate": 1.9688963761592984e-05, "loss": 0.3161, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.2275601249493782, "learning_rate": 1.963241759676897e-05, "loss": 0.3162, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.2613074784042425, "learning_rate": 1.9575874371124066e-05, "loss": 0.3406, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.24600961456588222, "learning_rate": 1.951933453677638e-05, "loss": 0.3062, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.264117569654962, "learning_rate": 1.9462798545816932e-05, "loss": 0.3194, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.25718410261258834, "learning_rate": 1.9406266850305996e-05, "loss": 0.3205, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.24313698864087252, "learning_rate": 1.9349739902269503e-05, "loss": 0.3232, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.2517963908083335, "learning_rate": 1.9293218153695425e-05, "loss": 0.3289, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2566706431598898, "learning_rate": 1.9236702056530153e-05, "loss": 0.3252, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.24632770320799552, "learning_rate": 1.9180192062674907e-05, "loss": 0.3278, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.2453602819525746, "learning_rate": 1.9123688623982076e-05, "loss": 0.3208, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.2729624943692456, "learning_rate": 1.906719219225165e-05, "loss": 0.3283, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.2632804003135972, "learning_rate": 1.9010703219227603e-05, "loss": 0.3168, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.26069734668864064, "learning_rate": 1.8954222156594256e-05, "loss": 0.3316, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.26084029154687405, "learning_rate": 1.8897749455972673e-05, "loss": 0.3378, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.28857553835099137, "learning_rate": 1.884128556891707e-05, "loss": 0.319, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.26911967547277316, "learning_rate": 1.878483094691119e-05, "loss": 0.3254, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.2342351996670823, "learning_rate": 1.8728386041364664e-05, "loss": 0.308, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.24461888051804198, "learning_rate": 1.867195130360947e-05, "loss": 0.3195, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.2505516717166395, "learning_rate": 1.8615527184896263e-05, "loss": 0.317, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.2234891162278957, "learning_rate": 1.8559114136390795e-05, "loss": 0.3174, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.2553116273167886, "learning_rate": 1.8502712609170298e-05, "loss": 0.3246, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.225507723249284, "learning_rate": 1.8446323054219876e-05, "loss": 0.3257, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.23573135362284786, "learning_rate": 1.838994592242891e-05, "loss": 0.3154, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.26791809545654666, "learning_rate": 1.8333581664587453e-05, "loss": 0.3291, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.27382666640972575, "learning_rate": 1.8277230731382593e-05, "loss": 0.3184, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.2729759132392533, "learning_rate": 1.82208935733949e-05, "loss": 0.3142, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.24769772038851529, "learning_rate": 1.8164570641094793e-05, "loss": 0.3266, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.23790753701670636, "learning_rate": 1.810826238483892e-05, "loss": 0.3311, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.2522173530359497, "learning_rate": 1.8051969254866608e-05, "loss": 0.3197, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.21895298033149357, "learning_rate": 1.7995691701296226e-05, "loss": 0.31, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.2228625220444671, "learning_rate": 1.7939430174121593e-05, "loss": 0.3148, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.2286656562765298, "learning_rate": 1.788318512320838e-05, "loss": 0.316, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.22374051242965956, "learning_rate": 1.782695699829051e-05, "loss": 0.3286, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.23509948812240034, "learning_rate": 1.7770746248966587e-05, "loss": 0.3269, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.222004100754247, "learning_rate": 1.7714553324696243e-05, "loss": 0.3247, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.24442769847378507, "learning_rate": 1.7658378674796614e-05, "loss": 0.3317, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.24488137512132244, "learning_rate": 1.76022227484387e-05, "loss": 0.3311, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.2571506382310766, "learning_rate": 1.7546085994643807e-05, "loss": 0.3253, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.23584846081933547, "learning_rate": 1.7489968862279902e-05, "loss": 0.3061, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.2589731271803909, "learning_rate": 1.743387180005809e-05, "loss": 0.3132, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.24830387293912495, "learning_rate": 1.737779525652899e-05, "loss": 0.3178, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2778799580525228, "learning_rate": 1.732173968007914e-05, "loss": 0.3258, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2627060748498032, "learning_rate": 1.7265705518927437e-05, "loss": 0.3237, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.2648872070729371, "learning_rate": 1.7209693221121542e-05, "loss": 0.3291, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.26673789745646087, "learning_rate": 1.7153703234534302e-05, "loss": 0.3212, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.23684655233360163, "learning_rate": 1.709773600686015e-05, "loss": 0.3172, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.2638735738873837, "learning_rate": 1.7041791985611548e-05, "loss": 0.3196, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.26446167873961435, "learning_rate": 1.69858716181154e-05, "loss": 0.3178, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.24986317134540528, "learning_rate": 1.692997535150948e-05, "loss": 0.3181, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.25834685933452234, "learning_rate": 1.687410363273884e-05, "loss": 0.3155, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.23891466910125722, "learning_rate": 1.6818256908552257e-05, "loss": 0.3186, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.26344389617658903, "learning_rate": 1.6762435625498646e-05, "loss": 0.3091, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.24913821505924452, "learning_rate": 1.67066402299235e-05, "loss": 0.3211, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.2397906236984009, "learning_rate": 1.6650871167965313e-05, "loss": 0.3217, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.23585288994315312, "learning_rate": 1.6595128885552028e-05, "loss": 0.3136, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.26727247054181075, "learning_rate": 1.653941382839745e-05, "loss": 0.3114, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.3680480981303409, "learning_rate": 1.6483726441997673e-05, "loss": 0.2679, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.348749940630128, "learning_rate": 1.642806717162757e-05, "loss": 0.2681, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.34836350550103734, "learning_rate": 1.637243646233718e-05, "loss": 0.2785, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.3396206233283949, "learning_rate": 1.6316834758948174e-05, "loss": 0.2719, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.32798271705922377, "learning_rate": 1.6261262506050282e-05, "loss": 0.2695, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.289742977792933, "learning_rate": 1.620572014799777e-05, "loss": 0.2709, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.33438676380508625, "learning_rate": 1.6150208128905857e-05, "loss": 0.271, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.29189948601776544, "learning_rate": 1.6094726892647147e-05, "loss": 0.2663, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.3043064063399002, "learning_rate": 1.6039276882848135e-05, "loss": 0.2654, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.27624221746058686, "learning_rate": 1.5983858542885635e-05, "loss": 0.2621, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.29218856016550604, "learning_rate": 1.5928472315883203e-05, "loss": 0.2635, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.2621398921272063, "learning_rate": 1.5873118644707633e-05, "loss": 0.2591, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.3048101645496301, "learning_rate": 1.5817797971965413e-05, "loss": 0.2642, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.29027393172511595, "learning_rate": 1.576251073999917e-05, "loss": 0.2676, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.26374278398448964, "learning_rate": 1.5707257390884126e-05, "loss": 0.2612, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.2704593205989109, "learning_rate": 1.5652038366424595e-05, "loss": 0.2716, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.2479735850242407, "learning_rate": 1.5596854108150424e-05, "loss": 0.2685, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.30214537207417824, "learning_rate": 1.5541705057313476e-05, "loss": 0.2692, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.24886989545831634, "learning_rate": 1.5486591654884086e-05, "loss": 0.2681, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.27521175856141356, "learning_rate": 1.543151434154755e-05, "loss": 0.2656, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.25313389104127537, "learning_rate": 1.5376473557700615e-05, "loss": 0.284, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.24298167865617903, "learning_rate": 1.5321469743447893e-05, "loss": 0.2675, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.24160942936817173, "learning_rate": 1.5266503338598434e-05, "loss": 0.2592, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.23391751013371156, "learning_rate": 1.5211574782662149e-05, "loss": 0.2646, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.2375709656845014, "learning_rate": 1.5156684514846307e-05, "loss": 0.2665, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2482500822390183, "learning_rate": 1.5101832974052012e-05, "loss": 0.2633, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.257107994662736, "learning_rate": 1.5047020598870737e-05, "loss": 0.2815, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2188166821090368, "learning_rate": 1.4992247827580778e-05, "loss": 0.2577, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.22835192387752476, "learning_rate": 1.493751509814374e-05, "loss": 0.2614, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.24269304359011298, "learning_rate": 1.4882822848201073e-05, "loss": 0.2607, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.2275063449115751, "learning_rate": 1.4828171515070553e-05, "loss": 0.2764, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.24216843398766327, "learning_rate": 1.4773561535742793e-05, "loss": 0.2672, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.21907027133088047, "learning_rate": 1.4718993346877715e-05, "loss": 0.2751, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.23425305682095865, "learning_rate": 1.466446738480111e-05, "loss": 0.2666, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.25168574928393384, "learning_rate": 1.460998408550112e-05, "loss": 0.2513, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.25745419750956033, "learning_rate": 1.4555543884624751e-05, "loss": 0.27, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.2603720570983712, "learning_rate": 1.4501147217474402e-05, "loss": 0.2626, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.25273505862437223, "learning_rate": 1.444679451900437e-05, "loss": 0.2657, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.2702742867187115, "learning_rate": 1.4392486223817397e-05, "loss": 0.2796, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.23265212746489008, "learning_rate": 1.4338222766161143e-05, "loss": 0.2635, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2652067822039291, "learning_rate": 1.4284004579924777e-05, "loss": 0.2717, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.24376632707409798, "learning_rate": 1.4229832098635479e-05, "loss": 0.2724, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.23477144265107472, "learning_rate": 1.4175705755454963e-05, "loss": 0.2661, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2484452070036021, "learning_rate": 1.412162598317602e-05, "loss": 0.2602, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.22350341198771095, "learning_rate": 1.406759321421907e-05, "loss": 0.2663, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2307173745523007, "learning_rate": 1.401360788062871e-05, "loss": 0.2752, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.2808256240889644, "learning_rate": 1.3959670414070204e-05, "loss": 0.2778, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.21660835921840574, "learning_rate": 1.3905781245826108e-05, "loss": 0.267, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.2579575312720767, "learning_rate": 1.3851940806792778e-05, "loss": 0.2694, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.21917187133421986, "learning_rate": 1.379814952747693e-05, "loss": 0.2632, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2403430204827632, "learning_rate": 1.3744407837992193e-05, "loss": 0.2743, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.24243816157518908, "learning_rate": 1.3690716168055692e-05, "loss": 0.2762, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.2399469699134233, "learning_rate": 1.363707494698459e-05, "loss": 0.2709, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.22742720699507954, "learning_rate": 1.358348460369265e-05, "loss": 0.2614, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.26851294464818937, "learning_rate": 1.352994556668684e-05, "loss": 0.2674, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.23582203206801922, "learning_rate": 1.3476458264063865e-05, "loss": 0.2838, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.2384933958782482, "learning_rate": 1.342302312350678e-05, "loss": 0.2881, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.2495461630409585, "learning_rate": 1.3369640572281537e-05, "loss": 0.2707, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.22740173473530367, "learning_rate": 1.3316311037233596e-05, "loss": 0.2779, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.23513236628560405, "learning_rate": 1.326303494478451e-05, "loss": 0.2829, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.22341868122763717, "learning_rate": 1.3209812720928472e-05, "loss": 0.2563, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.22231459950092342, "learning_rate": 1.315664479122898e-05, "loss": 0.2562, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.22261559880504025, "learning_rate": 1.3103531580815378e-05, "loss": 0.2716, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.22185031454874846, "learning_rate": 1.3050473514379488e-05, "loss": 0.2758, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.23005974606048754, "learning_rate": 1.2997471016172188e-05, "loss": 0.2676, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.21369002177005805, "learning_rate": 1.2944524510000042e-05, "loss": 0.2708, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.24194276840838902, "learning_rate": 1.2891634419221908e-05, "loss": 0.2869, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.22283284946251733, "learning_rate": 1.2838801166745545e-05, "loss": 0.2624, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.2226004269072867, "learning_rate": 1.2786025175024216e-05, "loss": 0.2745, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.23198195398555435, "learning_rate": 1.2733306866053357e-05, "loss": 0.2789, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.21919435336936444, "learning_rate": 1.2680646661367163e-05, "loss": 0.2816, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.22962796786364625, "learning_rate": 1.2628044982035219e-05, "loss": 0.2757, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.21273178409288643, "learning_rate": 1.2575502248659155e-05, "loss": 0.2684, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.21857080731968673, "learning_rate": 1.2523018881369269e-05, "loss": 0.2674, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2054506145644732, "learning_rate": 1.2470595299821176e-05, "loss": 0.2663, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.22809794032835773, "learning_rate": 1.2418231923192416e-05, "loss": 0.2651, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.22460919837011542, "learning_rate": 1.2365929170179165e-05, "loss": 0.2635, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.21594267483475055, "learning_rate": 1.2313687458992848e-05, "loss": 0.2656, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.21250000266110206, "learning_rate": 1.2261507207356785e-05, "loss": 0.2559, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.2225819548830283, "learning_rate": 1.220938883250288e-05, "loss": 0.2688, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.22302089627759578, "learning_rate": 1.215733275116827e-05, "loss": 0.2754, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.22096764408007094, "learning_rate": 1.2105339379592005e-05, "loss": 0.2676, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.21160900212251077, "learning_rate": 1.2053409133511681e-05, "loss": 0.2788, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.23012718546958455, "learning_rate": 1.2001542428160173e-05, "loss": 0.2645, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2018318585637087, "learning_rate": 1.1949739678262278e-05, "loss": 0.2633, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.22162376563345676, "learning_rate": 1.189800129803139e-05, "loss": 0.2714, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.2152037708475315, "learning_rate": 1.1846327701166228e-05, "loss": 0.2611, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.2100533379413434, "learning_rate": 1.1794719300847493e-05, "loss": 0.2606, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.21479136139522417, "learning_rate": 1.1743176509734582e-05, "loss": 0.2726, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2085537323516983, "learning_rate": 1.1691699739962275e-05, "loss": 0.2637, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.20259527794623897, "learning_rate": 1.1640289403137456e-05, "loss": 0.276, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.2305961173735981, "learning_rate": 1.1588945910335802e-05, "loss": 0.2726, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.1953239584883388, "learning_rate": 1.1537669672098517e-05, "loss": 0.2658, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.21687961251147383, "learning_rate": 1.1486461098429036e-05, "loss": 0.268, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.23181871298651277, "learning_rate": 1.1435320598789747e-05, "loss": 0.2694, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.2047240816156042, "learning_rate": 1.1384248582098736e-05, "loss": 0.2685, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.2154425528827126, "learning_rate": 1.1333245456726467e-05, "loss": 0.2762, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2160809083267957, "learning_rate": 1.128231163049258e-05, "loss": 0.2646, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.21442350423169484, "learning_rate": 1.123144751066259e-05, "loss": 0.2734, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.20557826729959047, "learning_rate": 1.1180653503944657e-05, "loss": 0.2698, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.20788903953840257, "learning_rate": 1.1129930016486287e-05, "loss": 0.2765, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.20680725058805008, "learning_rate": 1.107927745387114e-05, "loss": 0.2639, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.20629901165251302, "learning_rate": 1.1028696221115766e-05, "loss": 0.2623, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.20179927579653398, "learning_rate": 1.0978186722666341e-05, "loss": 0.2642, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.21852142622739176, "learning_rate": 1.0927749362395475e-05, "loss": 0.2569, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.21025526881743417, "learning_rate": 1.0877384543598954e-05, "loss": 0.2652, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.22339826883893651, "learning_rate": 1.0827092668992529e-05, "loss": 0.2783, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2092873080620356, "learning_rate": 1.077687414070869e-05, "loss": 0.2654, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.2146651253308813, "learning_rate": 1.0726729360293451e-05, "loss": 0.2613, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.2121385624453347, "learning_rate": 1.0676658728703147e-05, "loss": 0.2687, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.20501014234439716, "learning_rate": 1.0626662646301198e-05, "loss": 0.2644, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2112122829613544, "learning_rate": 1.0576741512854958e-05, "loss": 0.2564, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2081774850373381, "learning_rate": 1.052689572753247e-05, "loss": 0.2638, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2159245080113594, "learning_rate": 1.0477125688899328e-05, "loss": 0.274, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.2089390091076038, "learning_rate": 1.0427431794915406e-05, "loss": 0.2654, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.20928189654661003, "learning_rate": 1.0377814442931769e-05, "loss": 0.2753, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2101850235775703, "learning_rate": 1.0328274029687439e-05, "loss": 0.258, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.20985720118729814, "learning_rate": 1.0278810951306253e-05, "loss": 0.2743, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.19786270701903658, "learning_rate": 1.0229425603293647e-05, "loss": 0.2636, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.20575745406174042, "learning_rate": 1.0180118380533558e-05, "loss": 0.2729, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2076770305672794, "learning_rate": 1.0130889677285225e-05, "loss": 0.2629, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.20940241761228787, "learning_rate": 1.008173988718005e-05, "loss": 0.2667, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2067296440158572, "learning_rate": 1.0032669403218439e-05, "loss": 0.2548, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.21164497132290652, "learning_rate": 9.983678617766677e-06, "loss": 0.2785, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.22297948912689594, "learning_rate": 9.934767922553788e-06, "loss": 0.2716, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.20289138837020834, "learning_rate": 9.885937708668371e-06, "loss": 0.2737, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.20781120174498788, "learning_rate": 9.837188366555524e-06, "loss": 0.2718, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.22240070356924233, "learning_rate": 9.788520286013691e-06, "loss": 0.2764, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.19628273868846619, "learning_rate": 9.739933856191537e-06, "loss": 0.2631, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.20390795299369271, "learning_rate": 9.691429465584866e-06, "loss": 0.2697, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.19876039415873464, "learning_rate": 9.643007502033492e-06, "loss": 0.2645, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.2038291298332885, "learning_rate": 9.594668352718152e-06, "loss": 0.278, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.2040806232217708, "learning_rate": 9.546412404157383e-06, "loss": 0.2762, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.20547669649823475, "learning_rate": 9.498240042204471e-06, "loss": 0.2719, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.2040230424921687, "learning_rate": 9.450151652044339e-06, "loss": 0.259, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.21269383096794103, "learning_rate": 9.402147618190472e-06, "loss": 0.265, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.19463675341730413, "learning_rate": 9.354228324481841e-06, "loss": 0.2761, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.20672358351676234, "learning_rate": 9.306394154079852e-06, "loss": 0.2621, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.2139137883741086, "learning_rate": 9.258645489465254e-06, "loss": 0.2691, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.18514549965968616, "learning_rate": 9.21098271243509e-06, "loss": 0.2558, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.21920348998762018, "learning_rate": 9.163406204099659e-06, "loss": 0.2723, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.2136130007586193, "learning_rate": 9.115916344879452e-06, "loss": 0.266, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2048546241135086, "learning_rate": 9.068513514502126e-06, "loss": 0.2735, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.20654414750790115, "learning_rate": 9.021198091999439e-06, "loss": 0.2652, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.20060428933311497, "learning_rate": 8.973970455704251e-06, "loss": 0.2764, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.2171973084059094, "learning_rate": 8.926830983247495e-06, "loss": 0.2661, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2150054461332431, "learning_rate": 8.879780051555116e-06, "loss": 0.2677, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.22281456054125184, "learning_rate": 8.83281803684512e-06, "loss": 0.2748, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.21400855872879415, "learning_rate": 8.785945314624532e-06, "loss": 0.2805, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.21939567002536536, "learning_rate": 8.739162259686385e-06, "loss": 0.2664, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2013429374037822, "learning_rate": 8.692469246106734e-06, "loss": 0.2736, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.21028608210933716, "learning_rate": 8.645866647241677e-06, "loss": 0.2538, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.19705066228881624, "learning_rate": 8.599354835724348e-06, "loss": 0.2634, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.20261368293771118, "learning_rate": 8.552934183461958e-06, "loss": 0.2679, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.23356105757579534, "learning_rate": 8.506605061632805e-06, "loss": 0.2828, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.19598563256912155, "learning_rate": 8.460367840683308e-06, "loss": 0.2578, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.19963760128477545, "learning_rate": 8.414222890325065e-06, "loss": 0.2689, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.21141355180132862, "learning_rate": 8.368170579531855e-06, "loss": 0.272, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.19444466073737168, "learning_rate": 8.322211276536733e-06, "loss": 0.2578, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.21187422797346334, "learning_rate": 8.27634534882907e-06, "loss": 0.2658, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.22515211908255142, "learning_rate": 8.230573163151585e-06, "loss": 0.2679, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.2005365832944927, "learning_rate": 8.184895085497466e-06, "loss": 0.2749, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.2109977378867993, "learning_rate": 8.139311481107401e-06, "loss": 0.273, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.21020360698926863, "learning_rate": 8.093822714466686e-06, "loss": 0.2689, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.20274553294970496, "learning_rate": 8.048429149302271e-06, "loss": 0.266, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.20442016524587084, "learning_rate": 8.003131148579902e-06, "loss": 0.2584, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.215057430009318, "learning_rate": 7.957929074501182e-06, "loss": 0.2842, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.2004778868245099, "learning_rate": 7.912823288500695e-06, "loss": 0.2733, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.20227926851790468, "learning_rate": 7.867814151243102e-06, "loss": 0.2603, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.20262242381405443, "learning_rate": 7.822902022620267e-06, "loss": 0.2648, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.20775294099350247, "learning_rate": 7.778087261748377e-06, "loss": 0.279, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.19409517273030397, "learning_rate": 7.733370226965056e-06, "loss": 0.2712, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.19574566534585727, "learning_rate": 7.688751275826527e-06, "loss": 0.2629, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2220649974925048, "learning_rate": 7.644230765104735e-06, "loss": 0.2786, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.19537903502678655, "learning_rate": 7.599809050784502e-06, "loss": 0.2734, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.1946233520835663, "learning_rate": 7.555486488060661e-06, "loss": 0.2797, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.189500983499975, "learning_rate": 7.511263431335249e-06, "loss": 0.256, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.20640378096288084, "learning_rate": 7.467140234214656e-06, "loss": 0.2786, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.19490945146258137, "learning_rate": 7.423117249506777e-06, "loss": 0.2714, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.20050164691646102, "learning_rate": 7.379194829218231e-06, "loss": 0.2793, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.18833150540951152, "learning_rate": 7.335373324551518e-06, "loss": 0.2663, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.20047028158616467, "learning_rate": 7.291653085902224e-06, "loss": 0.2549, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.19084160160212343, "learning_rate": 7.248034462856213e-06, "loss": 0.2697, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.1936325373402579, "learning_rate": 7.20451780418683e-06, "loss": 0.2763, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2080095043775641, "learning_rate": 7.161103457852128e-06, "loss": 0.2585, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.1878378520207515, "learning_rate": 7.117791770992046e-06, "loss": 0.2538, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.19173635554919732, "learning_rate": 7.074583089925688e-06, "loss": 0.2707, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.21353359452435455, "learning_rate": 7.0314777601485155e-06, "loss": 0.2606, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.20588200410375182, "learning_rate": 6.988476126329604e-06, "loss": 0.2737, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.18568470174901475, "learning_rate": 6.945578532308857e-06, "loss": 0.2655, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.1960811885198192, "learning_rate": 6.902785321094301e-06, "loss": 0.2665, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.19994849575210527, "learning_rate": 6.8600968348593115e-06, "loss": 0.26, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.19837369553811324, "learning_rate": 6.817513414939892e-06, "loss": 0.2765, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.19345793057555347, "learning_rate": 6.775035401831924e-06, "loss": 0.2604, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.2116296406686844, "learning_rate": 6.732663135188473e-06, "loss": 0.2661, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.19883009689243988, "learning_rate": 6.690396953817055e-06, "loss": 0.2713, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.19549015526362803, "learning_rate": 6.648237195676927e-06, "loss": 0.2746, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.20539963611011539, "learning_rate": 6.606184197876395e-06, "loss": 0.2777, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.21265059158376104, "learning_rate": 6.564238296670109e-06, "loss": 0.2734, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.19928400850548308, "learning_rate": 6.52239982745638e-06, "loss": 0.2577, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.18583000386198753, "learning_rate": 6.480669124774484e-06, "loss": 0.2786, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.20625890049645376, "learning_rate": 6.439046522302013e-06, "loss": 0.268, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.21838899099981526, "learning_rate": 6.397532352852191e-06, "loss": 0.2623, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.19353013926128113, "learning_rate": 6.356126948371202e-06, "loss": 0.2752, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.18340603033484237, "learning_rate": 6.314830639935559e-06, "loss": 0.2605, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2135070107876705, "learning_rate": 6.273643757749448e-06, "loss": 0.2655, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.19492729032714198, "learning_rate": 6.2325666311420856e-06, "loss": 0.2643, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.19288546568625023, "learning_rate": 6.1915995885650675e-06, "loss": 0.2676, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.20189145512643888, "learning_rate": 6.150742957589784e-06, "loss": 0.2635, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.19619250867466348, "learning_rate": 6.109997064904774e-06, "loss": 0.2755, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.20249893076776254, "learning_rate": 6.069362236313092e-06, "loss": 0.2609, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.19551533528616596, "learning_rate": 6.0288387967297565e-06, "loss": 0.2767, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.1818697372610012, "learning_rate": 5.988427070179108e-06, "loss": 0.2675, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.1867003089743967, "learning_rate": 5.948127379792234e-06, "loss": 0.2653, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.19983107207127912, "learning_rate": 5.90794004780439e-06, "loss": 0.2652, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.19126339093708777, "learning_rate": 5.867865395552405e-06, "loss": 0.2656, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.18889126935393144, "learning_rate": 5.8279037434721364e-06, "loss": 0.2636, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.19061152485433494, "learning_rate": 5.788055411095892e-06, "loss": 0.2542, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2031545119094686, "learning_rate": 5.7483207170498625e-06, "loss": 0.2634, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.1849557587369144, "learning_rate": 5.708699979051613e-06, "loss": 0.2723, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.19427411316588197, "learning_rate": 5.66919351390751e-06, "loss": 0.2481, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.19322689613505828, "learning_rate": 5.629801637510188e-06, "loss": 0.258, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.19101250990485516, "learning_rate": 5.590524664836043e-06, "loss": 0.2746, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.19133899076889208, "learning_rate": 5.551362909942708e-06, "loss": 0.2564, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.202950278342339, "learning_rate": 5.51231668596653e-06, "loss": 0.2747, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.20608494481122205, "learning_rate": 5.47338630512007e-06, "loss": 0.2628, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.1893237787483964, "learning_rate": 5.434572078689617e-06, "loss": 0.2614, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.1827983027769305, "learning_rate": 5.395874317032694e-06, "loss": 0.261, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.19271718966516713, "learning_rate": 5.357293329575573e-06, "loss": 0.2564, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.19874989560135656, "learning_rate": 5.318829424810797e-06, "loss": 0.273, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.19885525214051572, "learning_rate": 5.280482910294728e-06, "loss": 0.265, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.18626301057685934, "learning_rate": 5.242254092645078e-06, "loss": 0.2618, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2021816988639359, "learning_rate": 5.2041432775384445e-06, "loss": 0.2695, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.19829587549934113, "learning_rate": 5.166150769707892e-06, "loss": 0.253, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.19600461810104733, "learning_rate": 5.128276872940503e-06, "loss": 0.2741, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.18816138089724435, "learning_rate": 5.090521890074953e-06, "loss": 0.2659, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2083240945760114, "learning_rate": 5.0528861229990675e-06, "loss": 0.2707, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.19533215913472274, "learning_rate": 5.015369872647442e-06, "loss": 0.2676, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.1906759974906458, "learning_rate": 4.9779734389990195e-06, "loss": 0.2705, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.18310236520717002, "learning_rate": 4.940697121074675e-06, "loss": 0.254, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.19586730762733315, "learning_rate": 4.903541216934864e-06, "loss": 0.2754, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.19001185328367476, "learning_rate": 4.8665060236772e-06, "loss": 0.2658, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.19796969415272878, "learning_rate": 4.829591837434102e-06, "loss": 0.2689, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.18417113331808033, "learning_rate": 4.792798953370424e-06, "loss": 0.2519, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.181830309599321, "learning_rate": 4.756127665681083e-06, "loss": 0.2468, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.19393124099805895, "learning_rate": 4.719578267588725e-06, "loss": 0.2846, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.19698407139504195, "learning_rate": 4.6831510513413525e-06, "loss": 0.2673, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.32959202462111126, "learning_rate": 4.6468463082100176e-06, "loss": 0.2374, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.2569349685717227, "learning_rate": 4.610664328486485e-06, "loss": 0.2291, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.25462000529307866, "learning_rate": 4.5746054014809e-06, "loss": 0.2291, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.36858925026744827, "learning_rate": 4.5386698155194766e-06, "loss": 0.2265, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.32183974049084507, "learning_rate": 4.502857857942204e-06, "loss": 0.2373, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.2375756682358064, "learning_rate": 4.467169815100549e-06, "loss": 0.2307, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.2997442855313304, "learning_rate": 4.431605972355137e-06, "loss": 0.2302, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.2928729862775259, "learning_rate": 4.396166614073516e-06, "loss": 0.2437, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.2086191147524675, "learning_rate": 4.360852023627846e-06, "loss": 0.2374, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.20999589026297305, "learning_rate": 4.325662483392656e-06, "loss": 0.2195, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2630936720207746, "learning_rate": 4.29059827474257e-06, "loss": 0.2297, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.2702025037486942, "learning_rate": 4.255659678050063e-06, "loss": 0.2425, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.20337393209016397, "learning_rate": 4.22084697268323e-06, "loss": 0.224, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.21071756953556248, "learning_rate": 4.186160437003535e-06, "loss": 0.2388, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.23551109074370347, "learning_rate": 4.151600348363582e-06, "loss": 0.2196, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.20401032294072224, "learning_rate": 4.11716698310493e-06, "loss": 0.2317, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.20514246574400827, "learning_rate": 4.082860616555848e-06, "loss": 0.2273, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.1940825793221557, "learning_rate": 4.048681523029125e-06, "loss": 0.2258, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.19131292942958492, "learning_rate": 4.014629975819882e-06, "loss": 0.2159, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.20871970202131213, "learning_rate": 3.9807062472033855e-06, "loss": 0.2394, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.20867250100168697, "learning_rate": 3.94691060843287e-06, "loss": 0.2283, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.20135507020675347, "learning_rate": 3.913243329737353e-06, "loss": 0.2352, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.18925481814045622, "learning_rate": 3.879704680319503e-06, "loss": 0.2319, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.191985363129816, "learning_rate": 3.846294928353471e-06, "loss": 0.2299, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.18666749884148973, "learning_rate": 3.8130143409827345e-06, "loss": 0.2172, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.173757141502914, "learning_rate": 3.7798631843179887e-06, "loss": 0.2321, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.18947615137432022, "learning_rate": 3.7468417234349973e-06, "loss": 0.2199, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.18339604315334274, "learning_rate": 3.7139502223724823e-06, "loss": 0.2258, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.18797628558009938, "learning_rate": 3.6811889441300095e-06, "loss": 0.2274, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.18037508510811395, "learning_rate": 3.648558150665886e-06, "loss": 0.226, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.18356247792958363, "learning_rate": 3.616058102895075e-06, "loss": 0.2324, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.18385783105284023, "learning_rate": 3.583689060687079e-06, "loss": 0.2315, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.18557567772775574, "learning_rate": 3.5514512828639023e-06, "loss": 0.2298, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.18742193578389907, "learning_rate": 3.51934502719796e-06, "loss": 0.2303, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.18196994748589468, "learning_rate": 3.4873705504100185e-06, "loss": 0.2267, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.1799594395680908, "learning_rate": 3.4555281081671345e-06, "loss": 0.2306, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.17920995865912337, "learning_rate": 3.4238179550806326e-06, "loss": 0.2373, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.18535378028505833, "learning_rate": 3.3922403447040497e-06, "loss": 0.2339, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.18540292007398151, "learning_rate": 3.3607955295311247e-06, "loss": 0.2273, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.18112520696145443, "learning_rate": 3.32948376099375e-06, "loss": 0.2249, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.19682815773057213, "learning_rate": 3.2983052894599976e-06, "loss": 0.2331, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.17942392758635273, "learning_rate": 3.2672603642320945e-06, "loss": 0.2291, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.18908436216157523, "learning_rate": 3.236349233544438e-06, "loss": 0.2168, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.17706710417416288, "learning_rate": 3.205572144561604e-06, "loss": 0.239, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.18314385264027955, "learning_rate": 3.174929343376374e-06, "loss": 0.2314, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.18990522315840158, "learning_rate": 3.1444210750077777e-06, "loss": 0.224, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.17964552695793948, "learning_rate": 3.1140475833991046e-06, "loss": 0.2309, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.1795977107454345, "learning_rate": 3.0838091114159895e-06, "loss": 0.2333, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.18393304534602686, "learning_rate": 3.0537059008444524e-06, "loss": 0.2293, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.18136647825936075, "learning_rate": 3.0237381923889563e-06, "loss": 0.2292, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.17709839091436932, "learning_rate": 2.9939062256704997e-06, "loss": 0.2134, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.17302539288241336, "learning_rate": 2.964210239224696e-06, "loss": 0.2241, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.17977589755207946, "learning_rate": 2.934650470499869e-06, "loss": 0.2133, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.18107767958151708, "learning_rate": 2.905227155855128e-06, "loss": 0.2359, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.17728916327384808, "learning_rate": 2.875940530558519e-06, "loss": 0.2197, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.17806369295303448, "learning_rate": 2.8467908287851154e-06, "loss": 0.226, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.1733484458379862, "learning_rate": 2.8177782836151603e-06, "loss": 0.2315, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.1829037759672887, "learning_rate": 2.7889031270321874e-06, "loss": 0.226, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.17894945175501037, "learning_rate": 2.760165589921184e-06, "loss": 0.2264, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.18188160885043925, "learning_rate": 2.7315659020667305e-06, "loss": 0.2155, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.17810590478816707, "learning_rate": 2.703104292151164e-06, "loss": 0.231, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.17944296342354274, "learning_rate": 2.6747809877527607e-06, "loss": 0.2322, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.17684114953365668, "learning_rate": 2.6465962153439082e-06, "loss": 0.2272, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.18178599938646756, "learning_rate": 2.618550200289303e-06, "loss": 0.2323, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.17695407206584773, "learning_rate": 2.59064316684412e-06, "loss": 0.2255, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.17978437169673905, "learning_rate": 2.562875338152264e-06, "loss": 0.2233, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.178925503093908, "learning_rate": 2.5352469362445552e-06, "loss": 0.2343, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.18475644535827884, "learning_rate": 2.5077581820369523e-06, "loss": 0.2417, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.17718987661936328, "learning_rate": 2.480409295328803e-06, "loss": 0.2218, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.1814855080671305, "learning_rate": 2.45320049480108e-06, "loss": 0.2248, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.17687162686413416, "learning_rate": 2.4261319980146293e-06, "loss": 0.2309, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.17807549271930817, "learning_rate": 2.399204021408421e-06, "loss": 0.2297, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.17824599121196177, "learning_rate": 2.3724167802978395e-06, "loss": 0.2339, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.2031989978328494, "learning_rate": 2.3457704888729625e-06, "loss": 0.2326, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.1717138664435552, "learning_rate": 2.3192653601968162e-06, "loss": 0.2232, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.1830015335062595, "learning_rate": 2.2929016062037057e-06, "loss": 0.2384, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.1721693558196337, "learning_rate": 2.2666794376975055e-06, "loss": 0.2269, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.17969610621480173, "learning_rate": 2.24059906434998e-06, "loss": 0.2221, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.18312072443774483, "learning_rate": 2.214660694699091e-06, "loss": 0.2175, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.1801599759038045, "learning_rate": 2.188864536147355e-06, "loss": 0.2192, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.1791361502237446, "learning_rate": 2.1632107949601757e-06, "loss": 0.2193, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.1758259265662688, "learning_rate": 2.137699676264171e-06, "loss": 0.235, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.17863776407259346, "learning_rate": 2.1123313840455738e-06, "loss": 0.2277, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.18637845566097802, "learning_rate": 2.08710612114857e-06, "loss": 0.2184, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.1791893877147315, "learning_rate": 2.0620240892736953e-06, "loss": 0.2336, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.17413451141867148, "learning_rate": 2.0370854889762e-06, "loss": 0.2369, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.18234904179047684, "learning_rate": 2.0122905196644726e-06, "loss": 0.232, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.17671960082649074, "learning_rate": 1.987639379598427e-06, "loss": 0.2341, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.17217364939556137, "learning_rate": 1.963132265887919e-06, "loss": 0.2242, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.17491244696734118, "learning_rate": 1.9387693744911784e-06, "loss": 0.2275, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.1779361235815849, "learning_rate": 1.9145509002132368e-06, "loss": 0.2234, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.17891812270990512, "learning_rate": 1.8904770367043723e-06, "loss": 0.2207, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.19191005410434753, "learning_rate": 1.8665479764585504e-06, "loss": 0.2315, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.1770995607891636, "learning_rate": 1.8427639108118977e-06, "loss": 0.2343, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.17698979611975257, "learning_rate": 1.8191250299411755e-06, "loss": 0.2312, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.1761309782652799, "learning_rate": 1.7956315228622446e-06, "loss": 0.2229, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.18414154131826704, "learning_rate": 1.7722835774285553e-06, "loss": 0.2228, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.17612327339546313, "learning_rate": 1.7490813803296624e-06, "loss": 0.2221, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.178222252871731, "learning_rate": 1.726025117089718e-06, "loss": 0.2276, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.17541872775319617, "learning_rate": 1.70311497206598e-06, "loss": 0.2258, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.16548861693970307, "learning_rate": 1.6803511284473638e-06, "loss": 0.2194, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.18313790711826733, "learning_rate": 1.6577337682529538e-06, "loss": 0.2335, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.17661701967596627, "learning_rate": 1.6352630723305617e-06, "loss": 0.2213, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.17304010646322354, "learning_rate": 1.612939220355272e-06, "loss": 0.2322, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.17453651254435187, "learning_rate": 1.5907623908280112e-06, "loss": 0.2361, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.17389813300437107, "learning_rate": 1.568732761074121e-06, "loss": 0.2252, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.17120234654032518, "learning_rate": 1.5468505072419237e-06, "loss": 0.2439, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.1796217508613131, "learning_rate": 1.5251158043013448e-06, "loss": 0.2423, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.17626986882778284, "learning_rate": 1.5035288260424885e-06, "loss": 0.229, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.1732626184468122, "learning_rate": 1.4820897450742623e-06, "loss": 0.2327, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.17516890115006153, "learning_rate": 1.4607987328229767e-06, "loss": 0.2305, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.168921566144624, "learning_rate": 1.4396559595310056e-06, "loss": 0.2283, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.1709151533101502, "learning_rate": 1.4186615942553973e-06, "loss": 0.2284, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.1736955400913589, "learning_rate": 1.3978158048665424e-06, "loss": 0.2394, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.17416249304139245, "learning_rate": 1.3771187580468115e-06, "loss": 0.2351, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.17647959913435565, "learning_rate": 1.3565706192892392e-06, "loss": 0.2275, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.1694603030372755, "learning_rate": 1.3361715528961993e-06, "loss": 0.2249, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.17121956910790656, "learning_rate": 1.3159217219780817e-06, "loss": 0.2361, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.1760639935798662, "learning_rate": 1.2958212884519949e-06, "loss": 0.2332, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.17041086293753585, "learning_rate": 1.2758704130404675e-06, "loss": 0.2289, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.17638781775573403, "learning_rate": 1.2560692552701738e-06, "loss": 0.2295, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.17601178401718326, "learning_rate": 1.2364179734706382e-06, "loss": 0.2374, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.17576891905401598, "learning_rate": 1.2169167247729852e-06, "loss": 0.2377, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.1743771273638881, "learning_rate": 1.1975656651086864e-06, "loss": 0.22, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.17959141355328645, "learning_rate": 1.1783649492082926e-06, "loss": 0.2229, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.17566404270664152, "learning_rate": 1.1593147306002183e-06, "loss": 0.2268, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.16806810684332177, "learning_rate": 1.140415161609505e-06, "loss": 0.2385, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.1770679418922285, "learning_rate": 1.121666393356604e-06, "loss": 0.2265, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.17032408391330736, "learning_rate": 1.1030685757561632e-06, "loss": 0.225, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.174422094839059, "learning_rate": 1.0846218575158373e-06, "loss": 0.2362, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.17447493634457836, "learning_rate": 1.066326386135097e-06, "loss": 0.2441, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.17252834696611868, "learning_rate": 1.0481823079040398e-06, "loss": 0.2315, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.17831515584354243, "learning_rate": 1.0301897679022344e-06, "loss": 0.2265, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.17662306040883569, "learning_rate": 1.0123489099975491e-06, "loss": 0.2266, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.17043142583232565, "learning_rate": 9.9465987684501e-07, "loss": 0.2161, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.1725728400996173, "learning_rate": 9.771228098856534e-07, "loss": 0.232, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.17196310349769225, "learning_rate": 9.597378493454013e-07, "loss": 0.2405, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.17186080895861516, "learning_rate": 9.425051342339353e-07, "loss": 0.2326, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.17423784147995364, "learning_rate": 9.254248023435864e-07, "loss": 0.2265, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.17384003569958303, "learning_rate": 9.084969902482288e-07, "loss": 0.2148, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.1686983337052322, "learning_rate": 8.917218333021993e-07, "loss": 0.2184, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.16485190528418084, "learning_rate": 8.750994656392109e-07, "loss": 0.2248, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.18058805376612486, "learning_rate": 8.58630020171265e-07, "loss": 0.2321, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.17718008864632923, "learning_rate": 8.423136285876099e-07, "loss": 0.2185, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.17153219111407453, "learning_rate": 8.26150421353682e-07, "loss": 0.2314, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.17056206329726828, "learning_rate": 8.101405277100549e-07, "loss": 0.2388, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.1763853644797225, "learning_rate": 7.942840756714077e-07, "loss": 0.2238, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.17115488910542392, "learning_rate": 7.785811920255093e-07, "loss": 0.2224, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.16769391433735215, "learning_rate": 7.630320023322024e-07, "loss": 0.2212, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.173624003292022, "learning_rate": 7.476366309223903e-07, "loss": 0.2355, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.17139788624246266, "learning_rate": 7.323952008970537e-07, "loss": 0.2275, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.17334761400163642, "learning_rate": 7.173078341262618e-07, "loss": 0.212, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.1810830005878639, "learning_rate": 7.023746512481989e-07, "loss": 0.2333, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.17350029675958523, "learning_rate": 6.875957716681902e-07, "loss": 0.2214, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.16816995849931682, "learning_rate": 6.729713135577687e-07, "loss": 0.232, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.17034319303451406, "learning_rate": 6.585013938537143e-07, "loss": 0.2352, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.17084506288228943, "learning_rate": 6.441861282571115e-07, "loss": 0.2272, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.16872184680649946, "learning_rate": 6.300256312324471e-07, "loss": 0.2224, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.17578269172698333, "learning_rate": 6.160200160066776e-07, "loss": 0.2347, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.17645320607439077, "learning_rate": 6.021693945683327e-07, "loss": 0.2329, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.16772239871977496, "learning_rate": 5.884738776666044e-07, "loss": 0.2271, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.17619249635270925, "learning_rate": 5.749335748104878e-07, "loss": 0.2249, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.1763500931235305, "learning_rate": 5.615485942678778e-07, "loss": 0.2202, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.17188725855326648, "learning_rate": 5.483190430647289e-07, "loss": 0.2208, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.1723075039962893, "learning_rate": 5.352450269841747e-07, "loss": 0.2342, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.1704882299372165, "learning_rate": 5.22326650565701e-07, "loss": 0.2383, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.17317865801856233, "learning_rate": 5.095640171043048e-07, "loss": 0.241, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.17287388913894577, "learning_rate": 4.969572286496594e-07, "loss": 0.2242, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.16868438026446675, "learning_rate": 4.845063860053079e-07, "loss": 0.2216, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.16987279857802629, "learning_rate": 4.7221158872785997e-07, "loss": 0.214, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.16875010778678784, "learning_rate": 4.600729351261857e-07, "loss": 0.2351, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.17256589807915018, "learning_rate": 4.4809052226063355e-07, "loss": 0.2246, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.17025293949391182, "learning_rate": 4.3626444594226046e-07, "loss": 0.2136, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.20180309914981712, "learning_rate": 4.245948007320588e-07, "loss": 0.2332, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.1647345376512716, "learning_rate": 4.130816799401971e-07, "loss": 0.2302, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.17419055796045968, "learning_rate": 4.017251756252827e-07, "loss": 0.2243, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.17453411754422726, "learning_rate": 3.9052537859362473e-07, "loss": 0.2358, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.1753998413940476, "learning_rate": 3.7948237839849687e-07, "loss": 0.2349, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.17433036308168112, "learning_rate": 3.6859626333943797e-07, "loss": 0.2152, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.16386111758804722, "learning_rate": 3.578671204615347e-07, "loss": 0.2342, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.17105732213990754, "learning_rate": 3.472950355547267e-07, "loss": 0.2434, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.17153978954717022, "learning_rate": 3.3688009315312244e-07, "loss": 0.2363, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.16589992105676782, "learning_rate": 3.266223765343224e-07, "loss": 0.2369, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.17213478131252846, "learning_rate": 3.16521967718757e-07, "loss": 0.2299, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.17104234318742456, "learning_rate": 3.0657894746902726e-07, "loss": 0.2312, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.1680794828117771, "learning_rate": 2.9679339528925654e-07, "loss": 0.2382, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.17138433771274594, "learning_rate": 2.871653894244597e-07, "loss": 0.2306, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.17311893031015985, "learning_rate": 2.7769500685991266e-07, "loss": 0.2243, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.1728706722781301, "learning_rate": 2.683823233205485e-07, "loss": 0.2337, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.17809339337879723, "learning_rate": 2.592274132703287e-07, "loss": 0.2238, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.17065713520259135, "learning_rate": 2.502303499116754e-07, "loss": 0.2258, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.1652906454468178, "learning_rate": 2.413912051848666e-07, "loss": 0.2309, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.17033155892584909, "learning_rate": 2.3271004976746613e-07, "loss": 0.2386, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.17080365425972083, "learning_rate": 2.2418695307376393e-07, "loss": 0.2329, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.16734758189973034, "learning_rate": 2.1582198325420968e-07, "loss": 0.23, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.1707143368057556, "learning_rate": 2.0761520719488447e-07, "loss": 0.2349, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.16535957327918394, "learning_rate": 1.9956669051694798e-07, "loss": 0.2175, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.1774273226305799, "learning_rate": 1.916764975761254e-07, "loss": 0.2245, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.17952930964132852, "learning_rate": 1.839446914621923e-07, "loss": 0.2376, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.16880065217606052, "learning_rate": 1.7637133399845962e-07, "loss": 0.2238, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.17578865466928167, "learning_rate": 1.6895648574129397e-07, "loss": 0.2245, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.16706024383208765, "learning_rate": 1.6170020597962465e-07, "loss": 0.2228, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.1631635301108217, "learning_rate": 1.5460255273447078e-07, "loss": 0.2121, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.16699769028681785, "learning_rate": 1.4766358275847715e-07, "loss": 0.2219, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.17106489966587432, "learning_rate": 1.4088335153546573e-07, "loss": 0.2206, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.16693070170808602, "learning_rate": 1.3426191327998496e-07, "loss": 0.2303, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.16877276850437245, "learning_rate": 1.277993209368744e-07, "loss": 0.2197, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.16532146498156258, "learning_rate": 1.214956261808542e-07, "loss": 0.2256, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.16928715178131715, "learning_rate": 1.1535087941609846e-07, "loss": 0.2322, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.16975492622367636, "learning_rate": 1.0936512977583802e-07, "loss": 0.2337, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.17030951430868765, "learning_rate": 1.0353842512196732e-07, "loss": 0.2314, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.1684318766989128, "learning_rate": 9.787081204466253e-08, "loss": 0.2352, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.16546753814356122, "learning_rate": 9.236233586200627e-08, "loss": 0.2215, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.16828519569089148, "learning_rate": 8.70130406196279e-08, "loss": 0.2384, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.19097132505818906, "learning_rate": 8.182296909035047e-08, "loss": 0.2322, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.1660089814470212, "learning_rate": 7.679216277384439e-08, "loss": 0.2295, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.17352237888249006, "learning_rate": 7.19206618963053e-08, "loss": 0.2338, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.1669549952961243, "learning_rate": 6.720850541012347e-08, "loss": 0.2407, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.1625821483987072, "learning_rate": 6.265573099357714e-08, "loss": 0.2319, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.16061812858615776, "learning_rate": 5.826237505053067e-08, "loss": 0.2281, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.1763196122109134, "learning_rate": 5.4028472710137e-08, "loss": 0.2389, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.17349767835804955, "learning_rate": 4.9954057826571146e-08, "loss": 0.2242, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.17365296748581602, "learning_rate": 4.6039162978743776e-08, "loss": 0.2127, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.1746644045830765, "learning_rate": 4.228381947004812e-08, "loss": 0.2294, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.1752555600983627, "learning_rate": 3.868805732811343e-08, "loss": 0.223, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.17160802836688646, "learning_rate": 3.525190530455636e-08, "loss": 0.2334, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.16885168498776976, "learning_rate": 3.197539087475887e-08, "loss": 0.2339, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.1638019828888362, "learning_rate": 2.8858540237641786e-08, "loss": 0.2263, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.16181909789976104, "learning_rate": 2.5901378315458247e-08, "loss": 0.2361, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.17004363244221737, "learning_rate": 2.3103928753598347e-08, "loss": 0.2328, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.1656582556241037, "learning_rate": 2.0466213920393718e-08, "loss": 0.2195, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.17137062620198298, "learning_rate": 1.7988254906942115e-08, "loss": 0.2306, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.16729514668953901, "learning_rate": 1.5670071526936447e-08, "loss": 0.2209, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.16692182676342301, "learning_rate": 1.3511682316509344e-08, "loss": 0.2381, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.18360967360398428, "learning_rate": 1.1513104534086605e-08, "loss": 0.2231, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.1695767810202596, "learning_rate": 9.67435416023843e-09, "loss": 0.2245, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.1709020695782397, "learning_rate": 7.995445897566178e-09, "loss": 0.2295, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.1771506275461289, "learning_rate": 6.476393170578021e-09, "loss": 0.2311, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.17602479846266786, "learning_rate": 5.11720812557348e-09, "loss": 0.2194, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.16896236779686005, "learning_rate": 3.917901630563492e-09, "loss": 0.2307, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.17460574242677232, "learning_rate": 2.878483275170485e-09, "loss": 0.2172, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.16726756286736494, "learning_rate": 1.998961370555108e-09, "loss": 0.2255, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.17415909143288885, "learning_rate": 1.2793429493518361e-09, "loss": 0.2211, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.16335742354139862, "learning_rate": 7.196337656112384e-10, "loss": 0.2368, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.17523813650644646, "learning_rate": 3.198382947511292e-10, "loss": 0.2269, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.16991414849333222, "learning_rate": 7.995973352770137e-11, "loss": 0.2377, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.17072910118059073, "learning_rate": 0.0, "loss": 0.2276, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 4.947037641766863e+18, "train_loss": 0.33841314686213425, "train_runtime": 29065.9332, "train_samples_per_second": 5.436, "train_steps_per_second": 0.042 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.947037641766863e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }