{ "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": 7.034244278962378, "learning_rate": 3.2258064516129035e-07, "loss": 0.8554, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.868589099486927, "learning_rate": 6.451612903225807e-07, "loss": 0.8414, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.031682016779269, "learning_rate": 9.67741935483871e-07, "loss": 0.8403, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.964179475710879, "learning_rate": 1.2903225806451614e-06, "loss": 0.835, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.704397329363464, "learning_rate": 1.6129032258064516e-06, "loss": 0.8249, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.34371679660721, "learning_rate": 1.935483870967742e-06, "loss": 0.823, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.145435391537434, "learning_rate": 2.2580645161290324e-06, "loss": 0.7756, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.965862936437879, "learning_rate": 2.580645161290323e-06, "loss": 0.7736, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.9929508902525037, "learning_rate": 2.903225806451613e-06, "loss": 0.7124, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.5559231688577473, "learning_rate": 3.225806451612903e-06, "loss": 0.7121, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.4687590135968804, "learning_rate": 3.548387096774194e-06, "loss": 0.7161, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.7289532492392916, "learning_rate": 3.870967741935484e-06, "loss": 0.6777, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.7686767439126134, "learning_rate": 4.193548387096774e-06, "loss": 0.6611, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.8734767169951803, "learning_rate": 4.516129032258065e-06, "loss": 0.6614, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.5238771562229054, "learning_rate": 4.838709677419355e-06, "loss": 0.6293, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.9955730518970127, "learning_rate": 5.161290322580646e-06, "loss": 0.6046, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.8925696381742494, "learning_rate": 5.483870967741935e-06, "loss": 0.5936, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.3897238385861175, "learning_rate": 5.806451612903226e-06, "loss": 0.582, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.031900534834639, "learning_rate": 6.129032258064517e-06, "loss": 0.596, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.3781666009754547, "learning_rate": 6.451612903225806e-06, "loss": 0.5606, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.4091380589698954, "learning_rate": 6.774193548387097e-06, "loss": 0.5589, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.6847037813145813, "learning_rate": 7.096774193548388e-06, "loss": 0.5655, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.4777955137341583, "learning_rate": 7.4193548387096784e-06, "loss": 0.5407, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.0867950123533463, "learning_rate": 7.741935483870968e-06, "loss": 0.5388, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.833858748635326, "learning_rate": 8.064516129032258e-06, "loss": 0.5145, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.0822371870824201, "learning_rate": 8.387096774193549e-06, "loss": 0.5171, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.0779429629636277, "learning_rate": 8.70967741935484e-06, "loss": 0.5156, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8636280769160924, "learning_rate": 9.03225806451613e-06, "loss": 0.4999, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.6948734772464383, "learning_rate": 9.35483870967742e-06, "loss": 0.4729, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7362633482466597, "learning_rate": 9.67741935483871e-06, "loss": 0.5171, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.936158226012926, "learning_rate": 1e-05, "loss": 0.5251, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.5965924380298965, "learning_rate": 1.0322580645161291e-05, "loss": 0.4954, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7224513066633772, "learning_rate": 1.0645161290322582e-05, "loss": 0.4898, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7762888913924452, "learning_rate": 1.096774193548387e-05, "loss": 0.4939, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.6582138008213901, "learning_rate": 1.1290322580645164e-05, "loss": 0.4959, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6801075139326265, "learning_rate": 1.1612903225806453e-05, "loss": 0.4676, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5970699047385664, "learning_rate": 1.1935483870967743e-05, "loss": 0.4688, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6331093391916344, "learning_rate": 1.2258064516129034e-05, "loss": 0.4645, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5417287115632764, "learning_rate": 1.2580645161290324e-05, "loss": 0.4656, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6298615348298016, "learning_rate": 1.2903225806451613e-05, "loss": 0.4676, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.5052497360953919, "learning_rate": 1.3225806451612903e-05, "loss": 0.4716, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.7028950635887516, "learning_rate": 1.3548387096774194e-05, "loss": 0.4657, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5853157016957827, "learning_rate": 1.3870967741935486e-05, "loss": 0.4654, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5685642913257054, "learning_rate": 1.4193548387096776e-05, "loss": 0.4728, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6184382011401869, "learning_rate": 1.4516129032258066e-05, "loss": 0.4491, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5969740103771383, "learning_rate": 1.4838709677419357e-05, "loss": 0.4582, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.543067907606544, "learning_rate": 1.5161290322580646e-05, "loss": 0.4389, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5864317578377521, "learning_rate": 1.5483870967741936e-05, "loss": 0.4491, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.4911869510582946, "learning_rate": 1.5806451612903226e-05, "loss": 0.448, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.5773946424274748, "learning_rate": 1.6129032258064517e-05, "loss": 0.4527, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5169426604184889, "learning_rate": 1.6451612903225807e-05, "loss": 0.4579, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.591788559097498, "learning_rate": 1.6774193548387098e-05, "loss": 0.4506, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.5896742351757768, "learning_rate": 1.7096774193548388e-05, "loss": 0.4478, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5009097029658488, "learning_rate": 1.741935483870968e-05, "loss": 0.4627, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.6015416166588835, "learning_rate": 1.774193548387097e-05, "loss": 0.4413, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6089212635092994, "learning_rate": 1.806451612903226e-05, "loss": 0.4323, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.5621782119404906, "learning_rate": 1.838709677419355e-05, "loss": 0.4576, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6657675372806421, "learning_rate": 1.870967741935484e-05, "loss": 0.4232, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.6248490230398297, "learning_rate": 1.903225806451613e-05, "loss": 0.4433, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.7005169473956325, "learning_rate": 1.935483870967742e-05, "loss": 0.4491, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.6808455229938818, "learning_rate": 1.967741935483871e-05, "loss": 0.4386, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.6163574469467545, "learning_rate": 2e-05, "loss": 0.4329, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5469093125741016, "learning_rate": 2.0322580645161292e-05, "loss": 0.4322, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7121581654586261, "learning_rate": 2.0645161290322582e-05, "loss": 0.4262, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.6160570494718784, "learning_rate": 2.0967741935483873e-05, "loss": 0.445, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.7080878364695875, "learning_rate": 2.1290322580645163e-05, "loss": 0.4374, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.6404922343017739, "learning_rate": 2.161290322580645e-05, "loss": 0.4341, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.5444947362115399, "learning_rate": 2.193548387096774e-05, "loss": 0.4343, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.6009434161874856, "learning_rate": 2.225806451612903e-05, "loss": 0.4264, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.6685469523039645, "learning_rate": 2.2580645161290328e-05, "loss": 0.4341, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7723422942559707, "learning_rate": 2.2903225806451615e-05, "loss": 0.4136, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7485896086494983, "learning_rate": 2.3225806451612906e-05, "loss": 0.4082, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.8747071224603636, "learning_rate": 2.3548387096774196e-05, "loss": 0.4509, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6999954614288543, "learning_rate": 2.3870967741935486e-05, "loss": 0.4417, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.7713559148590277, "learning_rate": 2.4193548387096777e-05, "loss": 0.4176, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.6023595050250846, "learning_rate": 2.4516129032258067e-05, "loss": 0.4385, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.7793385772954338, "learning_rate": 2.4838709677419358e-05, "loss": 0.4476, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.8692573418486464, "learning_rate": 2.5161290322580648e-05, "loss": 0.4341, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8645827768297322, "learning_rate": 2.548387096774194e-05, "loss": 0.4224, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.7079454161190654, "learning_rate": 2.5806451612903226e-05, "loss": 0.4213, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 1.0525279465289694, "learning_rate": 2.6129032258064516e-05, "loss": 0.4275, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.925068721496498, "learning_rate": 2.6451612903225806e-05, "loss": 0.421, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.69550423703778, "learning_rate": 2.6774193548387097e-05, "loss": 0.4265, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.8464233576514477, "learning_rate": 2.7096774193548387e-05, "loss": 0.4387, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.9465684615268425, "learning_rate": 2.7419354838709678e-05, "loss": 0.432, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.971473975263838, "learning_rate": 2.774193548387097e-05, "loss": 0.4314, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.6471191550652183, "learning_rate": 2.8064516129032262e-05, "loss": 0.4196, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.7639829620253273, "learning_rate": 2.8387096774193552e-05, "loss": 0.4332, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.888605847841124, "learning_rate": 2.8709677419354843e-05, "loss": 0.4352, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.6592417780540605, "learning_rate": 2.9032258064516133e-05, "loss": 0.4335, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.8689197937167733, "learning_rate": 2.9354838709677423e-05, "loss": 0.4307, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.0132750796914436, "learning_rate": 2.9677419354838714e-05, "loss": 0.4348, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.73442793640974, "learning_rate": 3.0000000000000004e-05, "loss": 0.4113, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7139866879122525, "learning_rate": 3.032258064516129e-05, "loss": 0.4353, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.6919741929881844, "learning_rate": 3.0645161290322585e-05, "loss": 0.4395, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.6358538938350136, "learning_rate": 3.096774193548387e-05, "loss": 0.4286, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.6159912820731417, "learning_rate": 3.1290322580645166e-05, "loss": 0.4242, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.6386303273640734, "learning_rate": 3.161290322580645e-05, "loss": 0.4366, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.6920418272579137, "learning_rate": 3.193548387096774e-05, "loss": 0.4133, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.7362382557122187, "learning_rate": 3.2258064516129034e-05, "loss": 0.4176, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.71670998858807, "learning_rate": 3.258064516129033e-05, "loss": 0.4188, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.5911185020319603, "learning_rate": 3.2903225806451614e-05, "loss": 0.4321, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.6211658961440604, "learning_rate": 3.322580645161291e-05, "loss": 0.4231, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.621618954580701, "learning_rate": 3.3548387096774195e-05, "loss": 0.406, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.6623713274515585, "learning_rate": 3.387096774193549e-05, "loss": 0.4333, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.5692263638946816, "learning_rate": 3.4193548387096776e-05, "loss": 0.4324, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.6729664252345631, "learning_rate": 3.451612903225807e-05, "loss": 0.4366, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.5709293885407117, "learning_rate": 3.483870967741936e-05, "loss": 0.4173, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.663322375465801, "learning_rate": 3.516129032258065e-05, "loss": 0.4368, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.5681814514067183, "learning_rate": 3.548387096774194e-05, "loss": 0.4293, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.5877791643444403, "learning_rate": 3.5806451612903225e-05, "loss": 0.4115, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.6069370882971127, "learning_rate": 3.612903225806452e-05, "loss": 0.4282, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.807308257077858, "learning_rate": 3.6451612903225805e-05, "loss": 0.4292, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.5652996448956293, "learning_rate": 3.67741935483871e-05, "loss": 0.405, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.7829875521043729, "learning_rate": 3.7096774193548386e-05, "loss": 0.4146, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6868080294353072, "learning_rate": 3.741935483870968e-05, "loss": 0.42, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.5801479303246624, "learning_rate": 3.7741935483870974e-05, "loss": 0.4128, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.6299938000616647, "learning_rate": 3.806451612903226e-05, "loss": 0.4067, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.9846586320595799, "learning_rate": 3.8387096774193555e-05, "loss": 0.4392, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.866108779632039, "learning_rate": 3.870967741935484e-05, "loss": 0.4254, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.7413597434669605, "learning_rate": 3.9032258064516135e-05, "loss": 0.4069, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6992056143028103, "learning_rate": 3.935483870967742e-05, "loss": 0.4289, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.8317223133678864, "learning_rate": 3.9677419354838716e-05, "loss": 0.4252, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7524919838869897, "learning_rate": 4e-05, "loss": 0.4136, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.5354900049519771, "learning_rate": 3.9999920040266474e-05, "loss": 0.4258, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.8282421670951283, "learning_rate": 3.999968016170525e-05, "loss": 0.4289, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.6950623028782837, "learning_rate": 3.9999280366234394e-05, "loss": 0.4336, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.585598711644341, "learning_rate": 3.999872065705065e-05, "loss": 0.4241, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.7793073255010041, "learning_rate": 3.999800103862945e-05, "loss": 0.4326, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.5694339030074848, "learning_rate": 3.9997121516724834e-05, "loss": 0.4535, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.552583222267051, "learning_rate": 3.999608209836944e-05, "loss": 0.4377, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.628352037869383, "learning_rate": 3.999488279187443e-05, "loss": 0.4088, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.6131347474527541, "learning_rate": 3.9993523606829425e-05, "loss": 0.4119, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.5622256765351384, "learning_rate": 3.9992004554102435e-05, "loss": 0.433, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.5808425438706519, "learning_rate": 3.999032564583976e-05, "loss": 0.4247, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.6183596396019465, "learning_rate": 3.998848689546591e-05, "loss": 0.4277, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.5815502734027423, "learning_rate": 3.9986488317683496e-05, "loss": 0.4254, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.6894071189431543, "learning_rate": 3.9984329928473067e-05, "loss": 0.4162, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.5809167993998421, "learning_rate": 3.998201174509306e-05, "loss": 0.4119, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.7125844967865038, "learning_rate": 3.997953378607961e-05, "loss": 0.4236, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.5683935708505832, "learning_rate": 3.9976896071246403e-05, "loss": 0.4137, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.5899456002307378, "learning_rate": 3.997409862168454e-05, "loss": 0.4434, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.62515934092467, "learning_rate": 3.997114145976237e-05, "loss": 0.418, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.4832727503886854, "learning_rate": 3.9968024609125245e-05, "loss": 0.4109, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.5886174147620731, "learning_rate": 3.996474809469545e-05, "loss": 0.389, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.5225357746303911, "learning_rate": 3.996131194267189e-05, "loss": 0.4217, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.5545683086667996, "learning_rate": 3.995771618052995e-05, "loss": 0.4207, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.5511117776755293, "learning_rate": 3.9953960837021256e-05, "loss": 0.4187, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.6257754009149233, "learning_rate": 3.995004594217343e-05, "loss": 0.4203, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7043252366173912, "learning_rate": 3.994597152728987e-05, "loss": 0.4343, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.595210374378218, "learning_rate": 3.994173762494947e-05, "loss": 0.4272, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.5759161551935204, "learning_rate": 3.9937344269006424e-05, "loss": 0.3985, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.6078824582608936, "learning_rate": 3.993279149458988e-05, "loss": 0.4126, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.5561293563390887, "learning_rate": 3.9928079338103695e-05, "loss": 0.4086, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.5414733019619152, "learning_rate": 3.992320783722616e-05, "loss": 0.4188, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.5310235653251582, "learning_rate": 3.991817703090965e-05, "loss": 0.4302, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.5540801909599945, "learning_rate": 3.991298695938038e-05, "loss": 0.4114, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6674866476289425, "learning_rate": 3.9907637664138e-05, "loss": 0.4081, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.4623059425427811, "learning_rate": 3.990212918795534e-05, "loss": 0.4323, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.649205304261789, "learning_rate": 3.9896461574878036e-05, "loss": 0.4042, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.4990629065083735, "learning_rate": 3.989063487022416e-05, "loss": 0.4027, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5121846177508738, "learning_rate": 3.9884649120583903e-05, "loss": 0.4225, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.4925537477474808, "learning_rate": 3.987850437381915e-05, "loss": 0.4112, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.5644429386837382, "learning_rate": 3.987220067906313e-05, "loss": 0.4196, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.5368176691602011, "learning_rate": 3.986573808672002e-05, "loss": 0.4041, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6697057383261046, "learning_rate": 3.9859116648464534e-05, "loss": 0.4211, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5060847612408336, "learning_rate": 3.985233641724152e-05, "loss": 0.4136, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.5400760930774953, "learning_rate": 3.984539744726554e-05, "loss": 0.4146, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.4951984483046377, "learning_rate": 3.983829979402038e-05, "loss": 0.4112, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.4533265658819627, "learning_rate": 3.983104351425871e-05, "loss": 0.418, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.5544425269410408, "learning_rate": 3.982362866600154e-05, "loss": 0.426, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.438982701928465, "learning_rate": 3.9816055308537806e-05, "loss": 0.3994, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.6091955289328203, "learning_rate": 3.980832350242388e-05, "loss": 0.3983, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5917719529156202, "learning_rate": 3.980043330948306e-05, "loss": 0.4089, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.5772282169626026, "learning_rate": 3.9792384792805124e-05, "loss": 0.4031, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.45315449893524273, "learning_rate": 3.978417801674579e-05, "loss": 0.4095, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.5645470415517401, "learning_rate": 3.9775813046926244e-05, "loss": 0.4042, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.43736962092602183, "learning_rate": 3.976728995023254e-05, "loss": 0.3975, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6304233717432665, "learning_rate": 3.975860879481514e-05, "loss": 0.4069, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.47281486254944044, "learning_rate": 3.974976965008833e-05, "loss": 0.4307, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.465034742292026, "learning_rate": 3.9740772586729674e-05, "loss": 0.408, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.42074260519714063, "learning_rate": 3.973161767667946e-05, "loss": 0.4283, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.44917616943391353, "learning_rate": 3.972230499314009e-05, "loss": 0.3934, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.448073696777058, "learning_rate": 3.9712834610575545e-05, "loss": 0.4094, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.42565117061517715, "learning_rate": 3.9703206604710746e-05, "loss": 0.4062, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.4770242245871197, "learning_rate": 3.969342105253098e-05, "loss": 0.4129, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.560385716306638, "learning_rate": 3.9683478032281246e-05, "loss": 0.4034, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5973545553716065, "learning_rate": 3.967337762346568e-05, "loss": 0.4071, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.4690823650672527, "learning_rate": 3.9663119906846885e-05, "loss": 0.4119, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.6844596959782259, "learning_rate": 3.965270496444528e-05, "loss": 0.4272, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.47132388767750055, "learning_rate": 3.9642132879538465e-05, "loss": 0.4149, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.4470243278171422, "learning_rate": 3.9631403736660566e-05, "loss": 0.3927, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5004380060827084, "learning_rate": 3.962051762160151e-05, "loss": 0.4165, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.3875988221590587, "learning_rate": 3.960947462140638e-05, "loss": 0.4022, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5662461326710836, "learning_rate": 3.959827482437472e-05, "loss": 0.421, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.653283404656978, "learning_rate": 3.958691832005981e-05, "loss": 0.4103, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5137579111722762, "learning_rate": 3.9575405199267944e-05, "loss": 0.4151, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.4243743934833243, "learning_rate": 3.956373555405774e-05, "loss": 0.406, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.50690924132071, "learning_rate": 3.955190947773937e-05, "loss": 0.4046, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.5164473720254497, "learning_rate": 3.9539927064873824e-05, "loss": 0.408, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.4383921810438391, "learning_rate": 3.952778841127214e-05, "loss": 0.4342, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5438972331925866, "learning_rate": 3.95154936139947e-05, "loss": 0.4105, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.4720570289730152, "learning_rate": 3.950304277135034e-05, "loss": 0.3888, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.47779223432036494, "learning_rate": 3.94904359828957e-05, "loss": 0.4252, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5625486250918861, "learning_rate": 3.94776733494343e-05, "loss": 0.3987, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.5241679675490021, "learning_rate": 3.9464754973015826e-05, "loss": 0.4296, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.4459234178213695, "learning_rate": 3.9451680956935275e-05, "loss": 0.397, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5071365349822164, "learning_rate": 3.943845140573213e-05, "loss": 0.4279, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.5084537904341246, "learning_rate": 3.942506642518952e-05, "loss": 0.4121, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.4622828589430294, "learning_rate": 3.9411526122333396e-05, "loss": 0.3929, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.4145834708799001, "learning_rate": 3.939783060543167e-05, "loss": 0.3975, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5753308863223596, "learning_rate": 3.938397998399333e-05, "loss": 0.4163, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.4259009569419552, "learning_rate": 3.936997436876756e-05, "loss": 0.402, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.4135397565039965, "learning_rate": 3.935581387174289e-05, "loss": 0.4196, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.4213857424783159, "learning_rate": 3.9341498606146295e-05, "loss": 0.4002, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.49515240423214046, "learning_rate": 3.932702868644224e-05, "loss": 0.3942, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.41585402042720376, "learning_rate": 3.931240422833181e-05, "loss": 0.3906, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5302026860014435, "learning_rate": 3.9297625348751806e-05, "loss": 0.41, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.4255074742890251, "learning_rate": 3.9282692165873744e-05, "loss": 0.4004, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.5142539498994062, "learning_rate": 3.9267604799102945e-05, "loss": 0.3952, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.40572729623400794, "learning_rate": 3.9252363369077615e-05, "loss": 0.4119, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5363923638058253, "learning_rate": 3.9236967997667796e-05, "loss": 0.4171, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.46219339871972837, "learning_rate": 3.9221418807974496e-05, "loss": 0.4035, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.44160934228906923, "learning_rate": 3.92057159243286e-05, "loss": 0.4051, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.522163452688863, "learning_rate": 3.9189859472289956e-05, "loss": 0.4067, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.5158337082544905, "learning_rate": 3.9173849578646324e-05, "loss": 0.3961, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.425794072288847, "learning_rate": 3.9157686371412395e-05, "loss": 0.4119, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5612651856441646, "learning_rate": 3.914136997982874e-05, "loss": 0.412, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5488603868856308, "learning_rate": 3.912490053436079e-05, "loss": 0.4027, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.42534975063150204, "learning_rate": 3.9108278166697805e-05, "loss": 0.398, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.4358395447975713, "learning_rate": 3.909150300975178e-05, "loss": 0.4086, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.38322788068344216, "learning_rate": 3.907457519765642e-05, "loss": 0.3919, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.432566694832425, "learning_rate": 3.905749486576607e-05, "loss": 0.4124, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.4299137542969717, "learning_rate": 3.90402621506546e-05, "loss": 0.3981, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4803076396839867, "learning_rate": 3.902287719011435e-05, "loss": 0.4039, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.4238632355748339, "learning_rate": 3.900534012315499e-05, "loss": 0.3961, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.41378248975379023, "learning_rate": 3.8987651090002454e-05, "loss": 0.4057, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.5838959077838815, "learning_rate": 3.896981023209777e-05, "loss": 0.3945, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.47780675575050163, "learning_rate": 3.8951817692095966e-05, "loss": 0.4261, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4631627101919882, "learning_rate": 3.893367361386491e-05, "loss": 0.4068, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.41863403360408225, "learning_rate": 3.891537814248417e-05, "loss": 0.4174, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4678624102167945, "learning_rate": 3.889693142424384e-05, "loss": 0.404, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.4163297714930713, "learning_rate": 3.8878333606643405e-05, "loss": 0.415, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.471722192765429, "learning_rate": 3.885958483839049e-05, "loss": 0.3985, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.46478625968524434, "learning_rate": 3.8840685269399786e-05, "loss": 0.3891, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.4066095074841943, "learning_rate": 3.882163505079171e-05, "loss": 0.4142, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5534180568221982, "learning_rate": 3.880243433489132e-05, "loss": 0.4012, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5102327751953082, "learning_rate": 3.878308327522702e-05, "loss": 0.3591, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.42269012001220324, "learning_rate": 3.876358202652936e-05, "loss": 0.3235, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.488182693359015, "learning_rate": 3.8743930744729835e-05, "loss": 0.3164, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.5032111594903025, "learning_rate": 3.8724129586959535e-05, "loss": 0.3346, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5265747091845598, "learning_rate": 3.870417871154801e-05, "loss": 0.3357, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.472089435347636, "learning_rate": 3.868407827802192e-05, "loss": 0.3277, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5214005805935586, "learning_rate": 3.8663828447103804e-05, "loss": 0.3408, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.47113687676829913, "learning_rate": 3.8643429380710765e-05, "loss": 0.3209, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5433731395339984, "learning_rate": 3.862288124195319e-05, "loss": 0.3108, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.4894950068287945, "learning_rate": 3.8602184195133464e-05, "loss": 0.3343, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5768775317759797, "learning_rate": 3.8581338405744604e-05, "loss": 0.3368, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.46635660314262406, "learning_rate": 3.8560344040468996e-05, "loss": 0.3318, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 6.796334853428008, "learning_rate": 3.853920126717703e-05, "loss": 0.3464, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.8925843379898976, "learning_rate": 3.851791025492574e-05, "loss": 0.3406, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.7387190973651044, "learning_rate": 3.8496471173957515e-05, "loss": 0.3261, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.679643286805371, "learning_rate": 3.847488419569866e-05, "loss": 0.3327, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.7328628312342841, "learning_rate": 3.8453149492758077e-05, "loss": 0.3495, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6238097737997034, "learning_rate": 3.8431267238925886e-05, "loss": 0.334, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.6240482891758234, "learning_rate": 3.840923760917199e-05, "loss": 0.3478, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5470184518708546, "learning_rate": 3.838706077964473e-05, "loss": 0.3211, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.6716646739230229, "learning_rate": 3.836473692766944e-05, "loss": 0.3306, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.49150702361786863, "learning_rate": 3.834226623174705e-05, "loss": 0.3575, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 1.0531978507403466, "learning_rate": 3.831964887155264e-05, "loss": 0.3345, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6267059318423105, "learning_rate": 3.829688502793403e-05, "loss": 0.3336, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.4670617203942455, "learning_rate": 3.827397488291029e-05, "loss": 0.3169, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.6284153313789591, "learning_rate": 3.8250918619670343e-05, "loss": 0.3354, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.42056137628587653, "learning_rate": 3.822771642257145e-05, "loss": 0.3376, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 4.54387189751086, "learning_rate": 3.820436847713776e-05, "loss": 0.3547, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.7835375773559556, "learning_rate": 3.8180874970058826e-05, "loss": 0.3683, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5954072663407486, "learning_rate": 3.8157236089188103e-05, "loss": 0.3368, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.8024417531167636, "learning_rate": 3.813345202354145e-05, "loss": 0.3401, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.5285004802209392, "learning_rate": 3.810952296329563e-05, "loss": 0.339, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.7161785184959657, "learning_rate": 3.808544909978676e-05, "loss": 0.3477, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.6429373838765012, "learning_rate": 3.806123062550882e-05, "loss": 0.3344, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.6320099162980951, "learning_rate": 3.803686773411208e-05, "loss": 0.3687, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.6793050488855906, "learning_rate": 3.801236062040158e-05, "loss": 0.3375, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5659018793625444, "learning_rate": 3.798770948033553e-05, "loss": 0.3424, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.6761573325791845, "learning_rate": 3.796291451102381e-05, "loss": 0.3624, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5180921503227327, "learning_rate": 3.793797591072631e-05, "loss": 0.3576, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6061811283089993, "learning_rate": 3.791289387885144e-05, "loss": 0.3366, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4066480651671704, "learning_rate": 3.788766861595443e-05, "loss": 0.334, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5402060287415545, "learning_rate": 3.7862300323735835e-05, "loss": 0.3163, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.48056024277273784, "learning_rate": 3.783678920503983e-05, "loss": 0.3207, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.5346845850397294, "learning_rate": 3.781113546385265e-05, "loss": 0.3315, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.46622143616420675, "learning_rate": 3.7785339305300916e-05, "loss": 0.3286, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.4727753227116511, "learning_rate": 3.7759400935650025e-05, "loss": 0.3304, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.518896949839672, "learning_rate": 3.77333205623025e-05, "loss": 0.3511, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.48767116801791, "learning_rate": 3.7707098393796295e-05, "loss": 0.3213, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5047824028597365, "learning_rate": 3.7680734639803185e-05, "loss": 0.3043, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5547597020781756, "learning_rate": 3.765422951112704e-05, "loss": 0.3414, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.512931747053154, "learning_rate": 3.762758321970216e-05, "loss": 0.3594, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.4084703567829268, "learning_rate": 3.7600795978591584e-05, "loss": 0.3479, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5134974819017761, "learning_rate": 3.757386800198538e-05, "loss": 0.3162, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.4494541213270734, "learning_rate": 3.7546799505198925e-05, "loss": 0.349, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5292954066342833, "learning_rate": 3.7519590704671197e-05, "loss": 0.3431, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.44819428728850885, "learning_rate": 3.749224181796305e-05, "loss": 0.3379, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.4691475792170118, "learning_rate": 3.746475306375545e-05, "loss": 0.3387, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.4494893740527283, "learning_rate": 3.743712466184774e-05, "loss": 0.3344, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.3744781760613138, "learning_rate": 3.7409356833155885e-05, "loss": 0.3316, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4664966326729779, "learning_rate": 3.73814497997107e-05, "loss": 0.3446, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.38275004950597963, "learning_rate": 3.7353403784656095e-05, "loss": 0.3247, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.38200642579801203, "learning_rate": 3.732521901224724e-05, "loss": 0.3392, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.3796028595451961, "learning_rate": 3.7296895707848844e-05, "loss": 0.3366, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.3323224060491625, "learning_rate": 3.7268434097933275e-05, "loss": 0.3302, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.3964087709187162, "learning_rate": 3.723983441007882e-05, "loss": 0.3259, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.3831110246904785, "learning_rate": 3.721109687296781e-05, "loss": 0.334, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.4025203579160111, "learning_rate": 3.718222171638484e-05, "loss": 0.3526, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.40768309288573124, "learning_rate": 3.715320917121488e-05, "loss": 0.3391, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.4066355147792603, "learning_rate": 3.712405946944149e-05, "loss": 0.3282, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.40109753341139276, "learning_rate": 3.709477284414488e-05, "loss": 0.3351, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.43244168914376374, "learning_rate": 3.7065349529500136e-05, "loss": 0.3386, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.3718619860633188, "learning_rate": 3.7035789760775305e-05, "loss": 0.3141, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.4157782561566406, "learning_rate": 3.70060937743295e-05, "loss": 0.3125, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.3870564890456344, "learning_rate": 3.6976261807611045e-05, "loss": 0.3367, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.4249684994033095, "learning_rate": 3.694629409915555e-05, "loss": 0.3259, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.395399849022025, "learning_rate": 3.691619088858401e-05, "loss": 0.3187, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.4453328592431511, "learning_rate": 3.68859524166009e-05, "loss": 0.3506, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.3867698417113223, "learning_rate": 3.6855578924992226e-05, "loss": 0.3379, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.4326397802281398, "learning_rate": 3.6825070656623626e-05, "loss": 0.3338, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.3717632483094601, "learning_rate": 3.67944278554384e-05, "loss": 0.3253, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4378991799845606, "learning_rate": 3.676365076645557e-05, "loss": 0.3207, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.3672109534235376, "learning_rate": 3.673273963576791e-05, "loss": 0.3349, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.37183911907066, "learning_rate": 3.670169471054001e-05, "loss": 0.3562, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.37633992071937133, "learning_rate": 3.6670516239006254e-05, "loss": 0.3525, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.36006384953688014, "learning_rate": 3.663920447046888e-05, "loss": 0.354, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.36753680375911174, "learning_rate": 3.6607759655295954e-05, "loss": 0.3429, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.41039650012882095, "learning_rate": 3.657618204491937e-05, "loss": 0.3435, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.3781834745218457, "learning_rate": 3.6544471891832875e-05, "loss": 0.3259, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.3703736110800969, "learning_rate": 3.6512629449589983e-05, "loss": 0.3393, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.3707962467007507, "learning_rate": 3.6480654972802045e-05, "loss": 0.3358, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.3599102819664536, "learning_rate": 3.644854871713611e-05, "loss": 0.3496, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.41132386868394677, "learning_rate": 3.6416310939312924e-05, "loss": 0.3407, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.3887339496688192, "learning_rate": 3.638394189710493e-05, "loss": 0.3444, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.41112000899278717, "learning_rate": 3.635144184933412e-05, "loss": 0.3426, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.3947293983895018, "learning_rate": 3.6318811055869994e-05, "loss": 0.3133, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.44228039074748626, "learning_rate": 3.628604977762752e-05, "loss": 0.3344, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.4757004354197209, "learning_rate": 3.6253158276565004e-05, "loss": 0.3341, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.4542728213566828, "learning_rate": 3.6220136815682016e-05, "loss": 0.3345, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.419517398039756, "learning_rate": 3.618698565901727e-05, "loss": 0.3388, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.43823528748831386, "learning_rate": 3.615370507164654e-05, "loss": 0.3046, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5293735822098731, "learning_rate": 3.61202953196805e-05, "loss": 0.3295, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.4439341789059211, "learning_rate": 3.6086756670262654e-05, "loss": 0.3532, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4854110817266567, "learning_rate": 3.6053089391567135e-05, "loss": 0.3158, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.42846577355084664, "learning_rate": 3.601929375279662e-05, "loss": 0.343, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.39203703709306026, "learning_rate": 3.598537002418012e-05, "loss": 0.3489, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.4384936852296385, "learning_rate": 3.5951318476970885e-05, "loss": 0.3498, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.38358405794000966, "learning_rate": 3.591713938344416e-05, "loss": 0.3318, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.4894219606899883, "learning_rate": 3.588283301689507e-05, "loss": 0.339, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.3552623973674264, "learning_rate": 3.5848399651636424e-05, "loss": 0.3373, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.3645701567056392, "learning_rate": 3.5813839562996473e-05, "loss": 0.3488, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.41154924184359765, "learning_rate": 3.5779153027316775e-05, "loss": 0.341, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.40256230274155014, "learning_rate": 3.574434032194994e-05, "loss": 0.336, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.4325439349307977, "learning_rate": 3.5709401725257436e-05, "loss": 0.3512, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.3833025398469958, "learning_rate": 3.5674337516607346e-05, "loss": 0.3356, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.3924634588268628, "learning_rate": 3.563914797637216e-05, "loss": 0.339, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.426307363299072, "learning_rate": 3.560383338592649e-05, "loss": 0.3352, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.44041059234706975, "learning_rate": 3.556839402764487e-05, "loss": 0.3311, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.45895466676187013, "learning_rate": 3.553283018489946e-05, "loss": 0.321, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.43012539661655863, "learning_rate": 3.54971421420578e-05, "loss": 0.3373, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.3661330603980039, "learning_rate": 3.5461330184480524e-05, "loss": 0.3287, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4609997494360588, "learning_rate": 3.54253945985191e-05, "loss": 0.3384, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.3855431139541199, "learning_rate": 3.5389335671513524e-05, "loss": 0.3362, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.4183398220525874, "learning_rate": 3.5353153691789986e-05, "loss": 0.3259, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.418918813661967, "learning_rate": 3.531684894865866e-05, "loss": 0.3222, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.45032189369386477, "learning_rate": 3.528042173241128e-05, "loss": 0.3449, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4617004063910657, "learning_rate": 3.524387233431892e-05, "loss": 0.3262, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.37648248386305816, "learning_rate": 3.520720104662958e-05, "loss": 0.3349, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.42199191408443537, "learning_rate": 3.5170408162565904e-05, "loss": 0.3369, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.3781971333512081, "learning_rate": 3.513349397632281e-05, "loss": 0.3333, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4770223170385961, "learning_rate": 3.5096458783065145e-05, "loss": 0.3347, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.41356030179388503, "learning_rate": 3.505930287892533e-05, "loss": 0.3314, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.4803796612000112, "learning_rate": 3.502202656100099e-05, "loss": 0.3432, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.41329280726541195, "learning_rate": 3.498463012735256e-05, "loss": 0.3438, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.446361386092208, "learning_rate": 3.494711387700094e-05, "loss": 0.3337, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.4167494899730799, "learning_rate": 3.490947810992505e-05, "loss": 0.3338, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.3998406689258236, "learning_rate": 3.48717231270595e-05, "loss": 0.3445, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4360758796979601, "learning_rate": 3.483384923029211e-05, "loss": 0.3498, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.3982032852461538, "learning_rate": 3.479585672246156e-05, "loss": 0.3341, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.39164203242505596, "learning_rate": 3.4757745907354924e-05, "loss": 0.337, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.33941659813924985, "learning_rate": 3.471951708970527e-05, "loss": 0.3216, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4002626402291176, "learning_rate": 3.468117057518921e-05, "loss": 0.3263, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.35867949919270903, "learning_rate": 3.4642706670424426e-05, "loss": 0.3376, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.44009126334358784, "learning_rate": 3.460412568296731e-05, "loss": 0.3529, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.36320558387182794, "learning_rate": 3.456542792131039e-05, "loss": 0.338, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.37902392143416225, "learning_rate": 3.4526613694879936e-05, "loss": 0.326, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.34705709608567503, "learning_rate": 3.448768331403348e-05, "loss": 0.3385, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.3848560941891912, "learning_rate": 3.44486370900573e-05, "loss": 0.32, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.3603918115310638, "learning_rate": 3.440947533516396e-05, "loss": 0.3478, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.44546276928762457, "learning_rate": 3.4370198362489816e-05, "loss": 0.3368, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.3625238215792753, "learning_rate": 3.43308064860925e-05, "loss": 0.3428, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.492086328429113, "learning_rate": 3.4291300020948393e-05, "loss": 0.3346, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.3519269173929909, "learning_rate": 3.425167928295015e-05, "loss": 0.3433, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.47596878377318036, "learning_rate": 3.421194458890411e-05, "loss": 0.3336, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.3691801304361101, "learning_rate": 3.4172096256527865e-05, "loss": 0.3338, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.41961492228589087, "learning_rate": 3.4132134604447595e-05, "loss": 0.3318, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.400371147502105, "learning_rate": 3.409205995219561e-05, "loss": 0.3437, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.40856631628369205, "learning_rate": 3.4051872620207765e-05, "loss": 0.3395, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.41533954628702136, "learning_rate": 3.40115729298209e-05, "loss": 0.3395, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.34473986679075747, "learning_rate": 3.397116120327025e-05, "loss": 0.3439, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.37969624451532763, "learning_rate": 3.3930637763686916e-05, "loss": 0.3308, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.38010897676047467, "learning_rate": 3.389000293509524e-05, "loss": 0.3468, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.37542925375750746, "learning_rate": 3.3849257042410225e-05, "loss": 0.3426, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.4152622362266582, "learning_rate": 3.380840041143494e-05, "loss": 0.3246, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.34067164354917245, "learning_rate": 3.376743336885792e-05, "loss": 0.3626, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4010112904364036, "learning_rate": 3.372635624225055e-05, "loss": 0.3436, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.34294302128242216, "learning_rate": 3.3685169360064445e-05, "loss": 0.3431, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.3931507975774247, "learning_rate": 3.3643873051628804e-05, "loss": 0.3381, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.3761897781999284, "learning_rate": 3.3602467647147814e-05, "loss": 0.3525, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.3274257167172616, "learning_rate": 3.356095347769799e-05, "loss": 0.3336, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.41107050391344363, "learning_rate": 3.351933087522552e-05, "loss": 0.3397, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.31832392809440135, "learning_rate": 3.3477600172543626e-05, "loss": 0.3461, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.3966602259962716, "learning_rate": 3.3435761703329894e-05, "loss": 0.3488, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.37266796885308856, "learning_rate": 3.3393815802123606e-05, "loss": 0.3366, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.4004181648556374, "learning_rate": 3.335176280432308e-05, "loss": 0.3534, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.37750144783917233, "learning_rate": 3.330960304618295e-05, "loss": 0.324, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.3724139500205314, "learning_rate": 3.326733686481153e-05, "loss": 0.3181, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.42634984779202517, "learning_rate": 3.3224964598168084e-05, "loss": 0.3467, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.40122048782635633, "learning_rate": 3.318248658506012e-05, "loss": 0.3353, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.42471791876778403, "learning_rate": 3.313990316514069e-05, "loss": 0.3452, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.3927719488491934, "learning_rate": 3.309721467890571e-05, "loss": 0.3487, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.3845654363949128, "learning_rate": 3.305442146769115e-05, "loss": 0.3396, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.34764143864689057, "learning_rate": 3.30115238736704e-05, "loss": 0.3364, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.407751101654406, "learning_rate": 3.296852223985148e-05, "loss": 0.349, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3347484495479725, "learning_rate": 3.2925416910074315e-05, "loss": 0.3333, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.4540662812273289, "learning_rate": 3.288220822900796e-05, "loss": 0.3475, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.35232294943220266, "learning_rate": 3.283889654214788e-05, "loss": 0.3353, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.3560616579291546, "learning_rate": 3.279548219581317e-05, "loss": 0.3266, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.38224388558264527, "learning_rate": 3.275196553714379e-05, "loss": 0.3241, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.37279554063476705, "learning_rate": 3.270834691409778e-05, "loss": 0.3239, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.3606458350705291, "learning_rate": 3.266462667544849e-05, "loss": 0.3185, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.4103939978652396, "learning_rate": 3.262080517078178e-05, "loss": 0.3407, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.392493895634111, "learning_rate": 3.257688275049323e-05, "loss": 0.3286, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.42721859950184726, "learning_rate": 3.253285976578535e-05, "loss": 0.3259, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.3783579198610759, "learning_rate": 3.2488736568664756e-05, "loss": 0.3416, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.4294108716232925, "learning_rate": 3.244451351193935e-05, "loss": 0.3199, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.3570616289172289, "learning_rate": 3.240019094921551e-05, "loss": 0.342, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.3314166543142198, "learning_rate": 3.235576923489527e-05, "loss": 0.3617, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.44310700739628917, "learning_rate": 3.2311248724173476e-05, "loss": 0.3321, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.3924520026988997, "learning_rate": 3.226662977303494e-05, "loss": 0.3272, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.45625951172369583, "learning_rate": 3.2221912738251626e-05, "loss": 0.3544, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.43633768689026536, "learning_rate": 3.2177097977379736e-05, "loss": 0.3541, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.369737796034698, "learning_rate": 3.21321858487569e-05, "loss": 0.3252, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4338514833722668, "learning_rate": 3.208717671149931e-05, "loss": 0.3137, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.39844240073950193, "learning_rate": 3.204207092549882e-05, "loss": 0.3178, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.43944614771271034, "learning_rate": 3.19968688514201e-05, "loss": 0.3342, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.4288095378673433, "learning_rate": 3.195157085069774e-05, "loss": 0.3427, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.38049547971325937, "learning_rate": 3.190617728553332e-05, "loss": 0.3316, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.40268445450815654, "learning_rate": 3.1860688518892606e-05, "loss": 0.3503, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4967694959572842, "learning_rate": 3.181510491450254e-05, "loss": 0.3457, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.3387865770821268, "learning_rate": 3.176942683684842e-05, "loss": 0.3319, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.4392465187220866, "learning_rate": 3.1723654651170934e-05, "loss": 0.3469, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.398122499731194, "learning_rate": 3.167778872346327e-05, "loss": 0.3369, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.4084248593999816, "learning_rate": 3.163182942046815e-05, "loss": 0.3333, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.3729101124584714, "learning_rate": 3.158577710967494e-05, "loss": 0.3331, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.4574600419261363, "learning_rate": 3.153963215931669e-05, "loss": 0.3484, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.3950830699549505, "learning_rate": 3.14933949383672e-05, "loss": 0.3248, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.4221920929549147, "learning_rate": 3.144706581653805e-05, "loss": 0.3539, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.39111557520358486, "learning_rate": 3.140064516427566e-05, "loss": 0.3398, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.362003319844568, "learning_rate": 3.135413335275833e-05, "loss": 0.3338, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.3978326289483315, "learning_rate": 3.130753075389327e-05, "loss": 0.3138, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.33328976092992413, "learning_rate": 3.1260837740313625e-05, "loss": 0.3395, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.3808623272580682, "learning_rate": 3.121405468537547e-05, "loss": 0.3231, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.3851620101828373, "learning_rate": 3.116718196315488e-05, "loss": 0.3272, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.380575688277509, "learning_rate": 3.1120219948444894e-05, "loss": 0.3418, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.42075862115811763, "learning_rate": 3.107316901675252e-05, "loss": 0.3414, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3902229688257327, "learning_rate": 3.1026029544295745e-05, "loss": 0.326, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.3408779473879343, "learning_rate": 3.097880190800057e-05, "loss": 0.3207, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.4153395375568873, "learning_rate": 3.093148648549788e-05, "loss": 0.3149, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.332150805271362, "learning_rate": 3.088408365512055e-05, "loss": 0.3323, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.35595108539576453, "learning_rate": 3.083659379590034e-05, "loss": 0.3502, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.4228726561688572, "learning_rate": 3.0789017287564913e-05, "loss": 0.3439, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.3842018480117158, "learning_rate": 3.074135451053475e-05, "loss": 0.337, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3648136720717963, "learning_rate": 3.069360584592015e-05, "loss": 0.3231, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.35255281771995306, "learning_rate": 3.064577167551816e-05, "loss": 0.3329, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.3642793274112826, "learning_rate": 3.059785238180953e-05, "loss": 0.3397, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.37312757960865534, "learning_rate": 3.054984834795566e-05, "loss": 0.3315, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.359166185818549, "learning_rate": 3.0501759957795537e-05, "loss": 0.3414, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.38368328663327694, "learning_rate": 3.0453587595842627e-05, "loss": 0.3441, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4104239422082927, "learning_rate": 3.0405331647281856e-05, "loss": 0.3212, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.4387619826459383, "learning_rate": 3.0356992497966508e-05, "loss": 0.3577, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3839819487054061, "learning_rate": 3.0308570534415137e-05, "loss": 0.3212, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.43554469522692335, "learning_rate": 3.0260066143808467e-05, "loss": 0.3434, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.36989216168984285, "learning_rate": 3.021147971398632e-05, "loss": 0.3355, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.4371815321804914, "learning_rate": 3.0162811633444478e-05, "loss": 0.3475, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.33522770433637955, "learning_rate": 3.0114062291331635e-05, "loss": 0.3329, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.39869523260319156, "learning_rate": 3.0065232077446217e-05, "loss": 0.3481, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.3587449693783028, "learning_rate": 3.001632138223332e-05, "loss": 0.3387, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.5450141309755445, "learning_rate": 2.9967330596781565e-05, "loss": 0.2709, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.37900858615896704, "learning_rate": 2.9918260112819952e-05, "loss": 0.2572, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.8610469285833772, "learning_rate": 2.9869110322714778e-05, "loss": 0.2494, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5042326305220666, "learning_rate": 2.9819881619466447e-05, "loss": 0.2446, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.48642580692756066, "learning_rate": 2.9770574396706364e-05, "loss": 0.262, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.42580610660462653, "learning_rate": 2.972118904869376e-05, "loss": 0.2417, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.38183326226667275, "learning_rate": 2.9671725970312563e-05, "loss": 0.2618, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5010413124879833, "learning_rate": 2.9622185557068238e-05, "loss": 0.2684, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.427063427847508, "learning_rate": 2.95725682050846e-05, "loss": 0.237, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.44607494329006575, "learning_rate": 2.9522874311100684e-05, "loss": 0.2431, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.46800577034351387, "learning_rate": 2.9473104272467526e-05, "loss": 0.2538, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.40606216890897767, "learning_rate": 2.942325848714505e-05, "loss": 0.2591, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.48548428322212644, "learning_rate": 2.9373337353698804e-05, "loss": 0.2217, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.41705808636768193, "learning_rate": 2.932334127129686e-05, "loss": 0.2585, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.43884467992054615, "learning_rate": 2.9273270639706547e-05, "loss": 0.2546, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.4494271365902733, "learning_rate": 2.922312585929131e-05, "loss": 0.2496, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.41294883834492674, "learning_rate": 2.9172907331007478e-05, "loss": 0.235, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.4456181665937126, "learning_rate": 2.9122615456401053e-05, "loss": 0.2479, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.4304052048119337, "learning_rate": 2.9072250637604535e-05, "loss": 0.2592, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.41505134778907754, "learning_rate": 2.9021813277333667e-05, "loss": 0.2566, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.5065426723686013, "learning_rate": 2.8971303778884244e-05, "loss": 0.2372, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.36326766746537464, "learning_rate": 2.8920722546128863e-05, "loss": 0.2497, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.43373692645010037, "learning_rate": 2.887006998351372e-05, "loss": 0.2514, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3543955658571473, "learning_rate": 2.881934649605535e-05, "loss": 0.2497, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.401390039225832, "learning_rate": 2.8768552489337408e-05, "loss": 0.257, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.3710412649907271, "learning_rate": 2.8717688369507425e-05, "loss": 0.2421, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.3382756082164605, "learning_rate": 2.8666754543273535e-05, "loss": 0.2423, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.3498896886733802, "learning_rate": 2.8615751417901273e-05, "loss": 0.2532, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.32463207297989893, "learning_rate": 2.856467940121025e-05, "loss": 0.2396, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.354781916550612, "learning_rate": 2.8513538901570964e-05, "loss": 0.2338, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.40621076447336324, "learning_rate": 2.846233032790149e-05, "loss": 0.2636, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.33170111354969856, "learning_rate": 2.84110540896642e-05, "loss": 0.2385, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.3585360765649011, "learning_rate": 2.8359710596862555e-05, "loss": 0.2494, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.37512512972416845, "learning_rate": 2.8308300260037734e-05, "loss": 0.2448, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3263190268444226, "learning_rate": 2.8256823490265424e-05, "loss": 0.255, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.35684571165853946, "learning_rate": 2.8205280699152515e-05, "loss": 0.2304, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.36502447463193494, "learning_rate": 2.8153672298833777e-05, "loss": 0.2534, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3196054987912658, "learning_rate": 2.8101998701968615e-05, "loss": 0.2353, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.3276781010807928, "learning_rate": 2.805026032173773e-05, "loss": 0.2515, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3484565980682967, "learning_rate": 2.7998457571839832e-05, "loss": 0.2475, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.3735551079180193, "learning_rate": 2.7946590866488322e-05, "loss": 0.2497, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.3823476465403792, "learning_rate": 2.7894660620408e-05, "loss": 0.2494, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.34830756028864635, "learning_rate": 2.784266724883173e-05, "loss": 0.2621, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3713224830522974, "learning_rate": 2.7790611167497128e-05, "loss": 0.2451, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3332515138785708, "learning_rate": 2.7738492792643224e-05, "loss": 0.2491, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3401890558413884, "learning_rate": 2.768631254100716e-05, "loss": 0.241, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.36605830164249425, "learning_rate": 2.7634070829820836e-05, "loss": 0.2462, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.37163354599708, "learning_rate": 2.7581768076807592e-05, "loss": 0.2471, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.3493595207026977, "learning_rate": 2.7529404700178832e-05, "loss": 0.257, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3790546122692273, "learning_rate": 2.7476981118630735e-05, "loss": 0.2576, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.3268095165095578, "learning_rate": 2.742449775134085e-05, "loss": 0.247, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.35337579341373504, "learning_rate": 2.7371955017964788e-05, "loss": 0.2538, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.3567239501467154, "learning_rate": 2.7319353338632845e-05, "loss": 0.2476, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3184821263104377, "learning_rate": 2.7266693133946645e-05, "loss": 0.2446, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.345372996024053, "learning_rate": 2.7213974824975785e-05, "loss": 0.2551, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.32181363781408473, "learning_rate": 2.7161198833254464e-05, "loss": 0.2489, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.31826820779375536, "learning_rate": 2.7108365580778095e-05, "loss": 0.2715, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3512335185725403, "learning_rate": 2.705547548999996e-05, "loss": 0.2518, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.33608078052476653, "learning_rate": 2.7002528983827817e-05, "loss": 0.2475, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3539072685124602, "learning_rate": 2.6949526485620517e-05, "loss": 0.2397, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3493136461387815, "learning_rate": 2.6896468419184623e-05, "loss": 0.2335, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.3350760850522897, "learning_rate": 2.6843355208771024e-05, "loss": 0.2282, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3870761947434675, "learning_rate": 2.6790187279071536e-05, "loss": 0.2348, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.35638392827484255, "learning_rate": 2.67369650552155e-05, "loss": 0.2476, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.3705716265153404, "learning_rate": 2.6683688962766407e-05, "loss": 0.2264, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.38218373244301246, "learning_rate": 2.6630359427718468e-05, "loss": 0.2695, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.31770777031349473, "learning_rate": 2.6576976876493225e-05, "loss": 0.2579, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.38558398571431407, "learning_rate": 2.652354173593614e-05, "loss": 0.2329, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.34929527758331325, "learning_rate": 2.647005443331317e-05, "loss": 0.2376, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3740689987564177, "learning_rate": 2.6416515396307354e-05, "loss": 0.2422, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.34700966880767636, "learning_rate": 2.636292505301542e-05, "loss": 0.2649, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3552556568659625, "learning_rate": 2.630928383194431e-05, "loss": 0.2695, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3802660116423009, "learning_rate": 2.625559216200781e-05, "loss": 0.2689, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3345242453240242, "learning_rate": 2.620185047252308e-05, "loss": 0.2601, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.40507983357218286, "learning_rate": 2.614805919320723e-05, "loss": 0.237, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3370698165565451, "learning_rate": 2.6094218754173895e-05, "loss": 0.2429, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.38323616221034124, "learning_rate": 2.60403295859298e-05, "loss": 0.2343, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3970150034081221, "learning_rate": 2.5986392119371297e-05, "loss": 0.2415, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.3300462399371872, "learning_rate": 2.5932406785780928e-05, "loss": 0.2364, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.419554933163875, "learning_rate": 2.5878374016823987e-05, "loss": 0.2804, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.34421728430342896, "learning_rate": 2.5824294244545045e-05, "loss": 0.2508, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.3779271533939456, "learning_rate": 2.577016790136453e-05, "loss": 0.2722, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.38227198169440735, "learning_rate": 2.5715995420075225e-05, "loss": 0.2529, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.31962760150996705, "learning_rate": 2.5661777233838864e-05, "loss": 0.255, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3698815323348613, "learning_rate": 2.5607513776182616e-05, "loss": 0.2291, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3962085730669952, "learning_rate": 2.5553205480995633e-05, "loss": 0.2597, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.32790362196224565, "learning_rate": 2.5498852782525604e-05, "loss": 0.2519, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.37314517970628086, "learning_rate": 2.5444456115375252e-05, "loss": 0.2437, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3345783669396294, "learning_rate": 2.539001591449889e-05, "loss": 0.2386, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.3836746858463562, "learning_rate": 2.53355326151989e-05, "loss": 0.2471, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3429951554935966, "learning_rate": 2.5281006653122288e-05, "loss": 0.2363, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3450628057170568, "learning_rate": 2.5226438464257217e-05, "loss": 0.2528, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3558281055185601, "learning_rate": 2.5171828484929447e-05, "loss": 0.2683, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3705991242724377, "learning_rate": 2.5117177151798934e-05, "loss": 0.2621, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.33956569450375695, "learning_rate": 2.506248490185627e-05, "loss": 0.2554, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.3691673874973447, "learning_rate": 2.500775217241923e-05, "loss": 0.2485, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.35760762549767977, "learning_rate": 2.4952979401129266e-05, "loss": 0.2397, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.34620847724755327, "learning_rate": 2.4898167025948e-05, "loss": 0.252, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.36047860123834347, "learning_rate": 2.4843315485153703e-05, "loss": 0.2639, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.3298186352286328, "learning_rate": 2.4788425217337856e-05, "loss": 0.2431, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.3191213647110427, "learning_rate": 2.4733496661401572e-05, "loss": 0.2333, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.31017467806800436, "learning_rate": 2.4678530256552114e-05, "loss": 0.2597, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.31251469972737944, "learning_rate": 2.46235264422994e-05, "loss": 0.2471, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.3632701939517716, "learning_rate": 2.4568485658452452e-05, "loss": 0.2271, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.354516878512722, "learning_rate": 2.451340834511592e-05, "loss": 0.2391, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.32305454906048303, "learning_rate": 2.4458294942686528e-05, "loss": 0.2469, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.34815603945429957, "learning_rate": 2.440314589184958e-05, "loss": 0.2353, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.33689039673110616, "learning_rate": 2.434796163357541e-05, "loss": 0.2405, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.341588513022741, "learning_rate": 2.429274260911588e-05, "loss": 0.2561, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.29936875309403826, "learning_rate": 2.423748926000084e-05, "loss": 0.2426, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.331873908617152, "learning_rate": 2.418220202803459e-05, "loss": 0.243, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3611274062598166, "learning_rate": 2.412688135529237e-05, "loss": 0.2405, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.32630695685836975, "learning_rate": 2.4071527684116807e-05, "loss": 0.2565, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.3634210128572373, "learning_rate": 2.4016141457114372e-05, "loss": 0.2432, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.40618578772799113, "learning_rate": 2.396072311715187e-05, "loss": 0.267, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3754932011582943, "learning_rate": 2.3905273107352863e-05, "loss": 0.2366, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.3430722640219569, "learning_rate": 2.3849791871094157e-05, "loss": 0.2423, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.38519611527236935, "learning_rate": 2.379427985200223e-05, "loss": 0.2628, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3754195795896808, "learning_rate": 2.373873749394972e-05, "loss": 0.253, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.33547927087928486, "learning_rate": 2.3683165241051836e-05, "loss": 0.2482, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.37793324555221663, "learning_rate": 2.3627563537662823e-05, "loss": 0.2639, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.31621206374897654, "learning_rate": 2.3571932828372433e-05, "loss": 0.2531, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3628973334741159, "learning_rate": 2.351627355800233e-05, "loss": 0.2388, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.3433226776040361, "learning_rate": 2.346058617160256e-05, "loss": 0.2359, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.33424422055903064, "learning_rate": 2.3404871114447976e-05, "loss": 0.2432, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3664625099255956, "learning_rate": 2.334912883203469e-05, "loss": 0.235, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3552794561377977, "learning_rate": 2.3293359770076505e-05, "loss": 0.2478, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.36144062768803215, "learning_rate": 2.323756437450136e-05, "loss": 0.2335, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.3814680510671946, "learning_rate": 2.3181743091447754e-05, "loss": 0.2532, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.3181330940176838, "learning_rate": 2.3125896367261164e-05, "loss": 0.2576, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.32573153697138, "learning_rate": 2.307002464849052e-05, "loss": 0.2516, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.33479120647591737, "learning_rate": 2.30141283818846e-05, "loss": 0.2437, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.33441116202801796, "learning_rate": 2.2958208014388462e-05, "loss": 0.2384, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.31326282297978547, "learning_rate": 2.2902263993139857e-05, "loss": 0.2432, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.35589689311991607, "learning_rate": 2.2846296765465708e-05, "loss": 0.248, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3156744963847473, "learning_rate": 2.2790306778878465e-05, "loss": 0.2551, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.3497303259264398, "learning_rate": 2.273429448107257e-05, "loss": 0.2494, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3322153025149726, "learning_rate": 2.2678260319920868e-05, "loss": 0.2398, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.33512223062524665, "learning_rate": 2.262220474347102e-05, "loss": 0.262, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3044265871939275, "learning_rate": 2.2566128199941918e-05, "loss": 0.2576, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.3191204295286813, "learning_rate": 2.2510031137720104e-05, "loss": 0.2498, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.30907052853043515, "learning_rate": 2.2453914005356206e-05, "loss": 0.2626, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.31242015345079416, "learning_rate": 2.2397777251561302e-05, "loss": 0.2423, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3119871197578442, "learning_rate": 2.2341621325203393e-05, "loss": 0.2582, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.32695438917995867, "learning_rate": 2.2285446675303764e-05, "loss": 0.2608, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.32387302311481697, "learning_rate": 2.2229253751033423e-05, "loss": 0.2616, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.30114596973332247, "learning_rate": 2.2173043001709492e-05, "loss": 0.2451, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.32566390543246476, "learning_rate": 2.2116814876791627e-05, "loss": 0.2386, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.3236895890713979, "learning_rate": 2.2060569825878413e-05, "loss": 0.2591, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.30834445506882385, "learning_rate": 2.2004308298703777e-05, "loss": 0.2751, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.31167749141304185, "learning_rate": 2.1948030745133396e-05, "loss": 0.2317, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3210412825292254, "learning_rate": 2.1891737615161083e-05, "loss": 0.2364, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.31217161394713183, "learning_rate": 2.1835429358905218e-05, "loss": 0.2503, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.32398939736001253, "learning_rate": 2.17791064266051e-05, "loss": 0.2593, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.34150996868538624, "learning_rate": 2.172276926861741e-05, "loss": 0.2562, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.33266987439967394, "learning_rate": 2.166641833541255e-05, "loss": 0.255, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3132735835105419, "learning_rate": 2.161005407757109e-05, "loss": 0.253, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3238512836574748, "learning_rate": 2.155367694578013e-05, "loss": 0.2549, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.30579352154345446, "learning_rate": 2.1497287390829712e-05, "loss": 0.2369, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.33456138124324886, "learning_rate": 2.1440885863609208e-05, "loss": 0.2303, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.3353015783106416, "learning_rate": 2.1384472815103737e-05, "loss": 0.2496, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3214842739285641, "learning_rate": 2.1328048696390534e-05, "loss": 0.2455, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.34161543001193084, "learning_rate": 2.1271613958635342e-05, "loss": 0.2506, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.318303213513033, "learning_rate": 2.1215169053088825e-05, "loss": 0.2459, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.3413660347185015, "learning_rate": 2.1158714431082937e-05, "loss": 0.2397, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3364761512482253, "learning_rate": 2.110225054402733e-05, "loss": 0.2313, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.5731856497500176, "learning_rate": 2.1045777843405747e-05, "loss": 0.2899, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.33170306727608906, "learning_rate": 2.09892967807724e-05, "loss": 0.2471, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3293571714848034, "learning_rate": 2.093280780774835e-05, "loss": 0.2342, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.37507999121184493, "learning_rate": 2.087631137601793e-05, "loss": 0.2462, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3161774393245508, "learning_rate": 2.0819807937325104e-05, "loss": 0.2507, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.34007658598951623, "learning_rate": 2.0763297943469847e-05, "loss": 0.2364, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.34977539363599947, "learning_rate": 2.070678184630458e-05, "loss": 0.2646, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.3015250577394456, "learning_rate": 2.06502600977305e-05, "loss": 0.2599, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3734871935452456, "learning_rate": 2.0593733149694008e-05, "loss": 0.2695, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.30940568137031627, "learning_rate": 2.0537201454183074e-05, "loss": 0.2554, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3242704190240712, "learning_rate": 2.0480665463223626e-05, "loss": 0.2407, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.33814096109330555, "learning_rate": 2.042412562887594e-05, "loss": 0.245, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3106265229783009, "learning_rate": 2.0367582403231033e-05, "loss": 0.2447, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3150165236779215, "learning_rate": 2.0311036238407023e-05, "loss": 0.2424, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.3285208162005144, "learning_rate": 2.0254487586545534e-05, "loss": 0.2628, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3343469136065918, "learning_rate": 2.0197936899808088e-05, "loss": 0.2566, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3087202847761139, "learning_rate": 2.0141384630372466e-05, "loss": 0.2335, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.33983633050460565, "learning_rate": 2.0084831230429106e-05, "loss": 0.2397, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.3030563966703529, "learning_rate": 2.0028277152177492e-05, "loss": 0.249, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.328861343470447, "learning_rate": 1.9971722847822518e-05, "loss": 0.2429, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3069459013010505, "learning_rate": 1.99151687695709e-05, "loss": 0.2605, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.30059277558977027, "learning_rate": 1.9858615369627537e-05, "loss": 0.2521, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.30326905105740637, "learning_rate": 1.9802063100191916e-05, "loss": 0.2511, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.298232268095426, "learning_rate": 1.974551241345447e-05, "loss": 0.2793, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.3228399347191204, "learning_rate": 1.9688963761592984e-05, "loss": 0.2479, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.30951006504867, "learning_rate": 1.963241759676897e-05, "loss": 0.2461, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.3142524961908703, "learning_rate": 1.9575874371124066e-05, "loss": 0.2522, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.33305469068472776, "learning_rate": 1.951933453677638e-05, "loss": 0.249, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.3136754856805395, "learning_rate": 1.9462798545816932e-05, "loss": 0.2357, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.32958858149342996, "learning_rate": 1.9406266850305996e-05, "loss": 0.236, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.3163839321034772, "learning_rate": 1.9349739902269503e-05, "loss": 0.2373, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3137422440541969, "learning_rate": 1.9293218153695425e-05, "loss": 0.2467, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.30981421062092424, "learning_rate": 1.9236702056530153e-05, "loss": 0.2676, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.30649869997587686, "learning_rate": 1.9180192062674907e-05, "loss": 0.2528, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.30931870704240855, "learning_rate": 1.9123688623982076e-05, "loss": 0.2595, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.319617653510899, "learning_rate": 1.906719219225165e-05, "loss": 0.2482, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.32699493754130926, "learning_rate": 1.9010703219227603e-05, "loss": 0.2329, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.31384358969208553, "learning_rate": 1.8954222156594256e-05, "loss": 0.2556, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.33328360882815544, "learning_rate": 1.8897749455972673e-05, "loss": 0.262, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.3051108867204185, "learning_rate": 1.884128556891707e-05, "loss": 0.2387, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.3010090213960574, "learning_rate": 1.878483094691119e-05, "loss": 0.2323, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.3419309256278018, "learning_rate": 1.8728386041364664e-05, "loss": 0.2664, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.3199079165540725, "learning_rate": 1.867195130360947e-05, "loss": 0.2376, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3285625666542713, "learning_rate": 1.8615527184896263e-05, "loss": 0.2389, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.34545049912838277, "learning_rate": 1.8559114136390795e-05, "loss": 0.2456, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.32891205777086013, "learning_rate": 1.8502712609170298e-05, "loss": 0.247, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.3248659374097569, "learning_rate": 1.8446323054219876e-05, "loss": 0.2458, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.31135062453958173, "learning_rate": 1.838994592242891e-05, "loss": 0.2431, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.3163975788154273, "learning_rate": 1.8333581664587453e-05, "loss": 0.2309, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3065551761374956, "learning_rate": 1.8277230731382593e-05, "loss": 0.2417, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3125144662991923, "learning_rate": 1.82208935733949e-05, "loss": 0.2542, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.3185564728679007, "learning_rate": 1.8164570641094793e-05, "loss": 0.2374, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3179098047613593, "learning_rate": 1.810826238483892e-05, "loss": 0.241, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.30155301569454007, "learning_rate": 1.8051969254866608e-05, "loss": 0.263, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.28880789436155235, "learning_rate": 1.7995691701296226e-05, "loss": 0.2415, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.32463053396836056, "learning_rate": 1.7939430174121593e-05, "loss": 0.2437, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.3155186281262611, "learning_rate": 1.788318512320838e-05, "loss": 0.2298, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3255095690863864, "learning_rate": 1.782695699829051e-05, "loss": 0.2412, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.32025942238361543, "learning_rate": 1.7770746248966587e-05, "loss": 0.2521, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.3271071529668241, "learning_rate": 1.7714553324696243e-05, "loss": 0.2394, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.32743068840124856, "learning_rate": 1.7658378674796614e-05, "loss": 0.2427, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3347877409539017, "learning_rate": 1.76022227484387e-05, "loss": 0.2357, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.3338012425250763, "learning_rate": 1.7546085994643807e-05, "loss": 0.2605, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.31905953753041993, "learning_rate": 1.7489968862279902e-05, "loss": 0.2439, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3112841182883374, "learning_rate": 1.743387180005809e-05, "loss": 0.2433, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.32471291125762564, "learning_rate": 1.737779525652899e-05, "loss": 0.2393, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.31270564394687117, "learning_rate": 1.732173968007914e-05, "loss": 0.2555, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.3252620810250393, "learning_rate": 1.7265705518927437e-05, "loss": 0.2346, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.31135695545006653, "learning_rate": 1.7209693221121542e-05, "loss": 0.2698, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.3094660391676153, "learning_rate": 1.7153703234534302e-05, "loss": 0.2598, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.30804770292325223, "learning_rate": 1.709773600686015e-05, "loss": 0.2478, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.30298972406640556, "learning_rate": 1.7041791985611548e-05, "loss": 0.2532, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.3165174946625103, "learning_rate": 1.69858716181154e-05, "loss": 0.2424, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.3017298932811026, "learning_rate": 1.692997535150948e-05, "loss": 0.2581, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.300305062414737, "learning_rate": 1.687410363273884e-05, "loss": 0.2238, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3192317005868519, "learning_rate": 1.6818256908552257e-05, "loss": 0.2276, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3091376566492584, "learning_rate": 1.6762435625498646e-05, "loss": 0.2399, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3374659869042973, "learning_rate": 1.67066402299235e-05, "loss": 0.2252, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.3092768934283164, "learning_rate": 1.6650871167965313e-05, "loss": 0.2624, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.30404444052740354, "learning_rate": 1.6595128885552028e-05, "loss": 0.2363, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.3298145696298955, "learning_rate": 1.653941382839745e-05, "loss": 0.2534, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.4193323751771185, "learning_rate": 1.6483726441997673e-05, "loss": 0.1837, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3045169556499558, "learning_rate": 1.642806717162757e-05, "loss": 0.1723, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.413430442403963, "learning_rate": 1.637243646233718e-05, "loss": 0.1763, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.5647824985667932, "learning_rate": 1.6316834758948174e-05, "loss": 0.186, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.35386648860416164, "learning_rate": 1.6261262506050282e-05, "loss": 0.1967, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.41694597031151415, "learning_rate": 1.620572014799777e-05, "loss": 0.1674, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.4244225818326384, "learning_rate": 1.6150208128905857e-05, "loss": 0.1726, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.36041383076937994, "learning_rate": 1.6094726892647147e-05, "loss": 0.1743, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.28700048062223216, "learning_rate": 1.6039276882848135e-05, "loss": 0.1811, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.336699452955107, "learning_rate": 1.5983858542885635e-05, "loss": 0.1487, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3800819600432117, "learning_rate": 1.5928472315883203e-05, "loss": 0.1852, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.32037267118340074, "learning_rate": 1.5873118644707633e-05, "loss": 0.1675, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.2965176502355665, "learning_rate": 1.5817797971965413e-05, "loss": 0.1813, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.3085943225065413, "learning_rate": 1.576251073999917e-05, "loss": 0.178, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.3111437297715546, "learning_rate": 1.5707257390884126e-05, "loss": 0.1624, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.3206576528373887, "learning_rate": 1.5652038366424595e-05, "loss": 0.1912, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.31027459754771514, "learning_rate": 1.5596854108150424e-05, "loss": 0.1955, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3261072089577517, "learning_rate": 1.5541705057313476e-05, "loss": 0.1597, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.32091311505538517, "learning_rate": 1.5486591654884086e-05, "loss": 0.1853, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.27592359975950614, "learning_rate": 1.543151434154755e-05, "loss": 0.1749, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.3145572206133281, "learning_rate": 1.5376473557700615e-05, "loss": 0.1796, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.29681805691130286, "learning_rate": 1.5321469743447893e-05, "loss": 0.1891, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.2791464452677027, "learning_rate": 1.5266503338598434e-05, "loss": 0.166, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.29898691580621084, "learning_rate": 1.5211574782662149e-05, "loss": 0.1766, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3033671659786628, "learning_rate": 1.5156684514846307e-05, "loss": 0.1931, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2807869060609479, "learning_rate": 1.5101832974052012e-05, "loss": 0.1644, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.29453399497825294, "learning_rate": 1.5047020598870737e-05, "loss": 0.1669, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.28473841140435374, "learning_rate": 1.4992247827580778e-05, "loss": 0.1682, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.2812913298766966, "learning_rate": 1.493751509814374e-05, "loss": 0.1797, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.27148974795882364, "learning_rate": 1.4882822848201073e-05, "loss": 0.1793, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.28791885813574436, "learning_rate": 1.4828171515070553e-05, "loss": 0.1762, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2688408795562644, "learning_rate": 1.4773561535742793e-05, "loss": 0.1818, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.2749288609931789, "learning_rate": 1.4718993346877715e-05, "loss": 0.1889, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.2873795838047895, "learning_rate": 1.466446738480111e-05, "loss": 0.1952, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.2814291971541834, "learning_rate": 1.460998408550112e-05, "loss": 0.1711, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3084450625951882, "learning_rate": 1.4555543884624751e-05, "loss": 0.168, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.281613168183369, "learning_rate": 1.4501147217474402e-05, "loss": 0.1766, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.2834819006902462, "learning_rate": 1.444679451900437e-05, "loss": 0.1707, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.29574748208711044, "learning_rate": 1.4392486223817397e-05, "loss": 0.1715, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2845281382330222, "learning_rate": 1.4338222766161143e-05, "loss": 0.1673, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.27316454324953404, "learning_rate": 1.4284004579924777e-05, "loss": 0.1829, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.31121062354851337, "learning_rate": 1.4229832098635479e-05, "loss": 0.1581, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.2917621324126832, "learning_rate": 1.4175705755454963e-05, "loss": 0.1773, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2864059602008709, "learning_rate": 1.412162598317602e-05, "loss": 0.1899, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.26273293477289894, "learning_rate": 1.406759321421907e-05, "loss": 0.1854, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.27602247402426816, "learning_rate": 1.401360788062871e-05, "loss": 0.1772, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.28626889473701783, "learning_rate": 1.3959670414070204e-05, "loss": 0.175, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.27873522174383997, "learning_rate": 1.3905781245826108e-05, "loss": 0.1694, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.28904379442767064, "learning_rate": 1.3851940806792778e-05, "loss": 0.18, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.2878268642502106, "learning_rate": 1.379814952747693e-05, "loss": 0.1726, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2612236690167241, "learning_rate": 1.3744407837992193e-05, "loss": 0.178, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2864467646853813, "learning_rate": 1.3690716168055692e-05, "loss": 0.1756, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.27426075120964455, "learning_rate": 1.363707494698459e-05, "loss": 0.1689, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.26599242774296444, "learning_rate": 1.358348460369265e-05, "loss": 0.1645, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.28500736449205827, "learning_rate": 1.352994556668684e-05, "loss": 0.1802, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.28943844356170073, "learning_rate": 1.3476458264063865e-05, "loss": 0.178, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.28584029003867556, "learning_rate": 1.342302312350678e-05, "loss": 0.1598, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.27728136656055485, "learning_rate": 1.3369640572281537e-05, "loss": 0.166, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.2845744097421679, "learning_rate": 1.3316311037233596e-05, "loss": 0.1641, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2589243476658281, "learning_rate": 1.326303494478451e-05, "loss": 0.1741, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.27696876360902245, "learning_rate": 1.3209812720928472e-05, "loss": 0.1731, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2765367061123281, "learning_rate": 1.315664479122898e-05, "loss": 0.2022, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.2779813367684708, "learning_rate": 1.3103531580815378e-05, "loss": 0.1683, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.2759965978737665, "learning_rate": 1.3050473514379488e-05, "loss": 0.1722, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2735082637423241, "learning_rate": 1.2997471016172188e-05, "loss": 0.1754, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.26055813789329735, "learning_rate": 1.2944524510000042e-05, "loss": 0.1806, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.274656759402573, "learning_rate": 1.2891634419221908e-05, "loss": 0.1617, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.27071792378982523, "learning_rate": 1.2838801166745545e-05, "loss": 0.1631, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.266263478741566, "learning_rate": 1.2786025175024216e-05, "loss": 0.1864, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.2792606629477124, "learning_rate": 1.2733306866053357e-05, "loss": 0.1695, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2836745755570434, "learning_rate": 1.2680646661367163e-05, "loss": 0.1636, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.2731109814759349, "learning_rate": 1.2628044982035219e-05, "loss": 0.1665, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.2714761570382694, "learning_rate": 1.2575502248659155e-05, "loss": 0.16, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2856937643440585, "learning_rate": 1.2523018881369269e-05, "loss": 0.162, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.26148364907231314, "learning_rate": 1.2470595299821176e-05, "loss": 0.1807, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2586780823510922, "learning_rate": 1.2418231923192416e-05, "loss": 0.1704, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.3222941499602224, "learning_rate": 1.2365929170179165e-05, "loss": 0.1671, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.26724789529462384, "learning_rate": 1.2313687458992848e-05, "loss": 0.1863, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.2770387876451957, "learning_rate": 1.2261507207356785e-05, "loss": 0.178, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.2841587939160571, "learning_rate": 1.220938883250288e-05, "loss": 0.1802, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2728132570215387, "learning_rate": 1.215733275116827e-05, "loss": 0.1776, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.26888493946252795, "learning_rate": 1.2105339379592005e-05, "loss": 0.1768, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.27484396524786436, "learning_rate": 1.2053409133511681e-05, "loss": 0.1852, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.2862062105278399, "learning_rate": 1.2001542428160173e-05, "loss": 0.1662, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2697874794228325, "learning_rate": 1.1949739678262278e-05, "loss": 0.1799, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.28403341298629453, "learning_rate": 1.189800129803139e-05, "loss": 0.143, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.2778016635460589, "learning_rate": 1.1846327701166228e-05, "loss": 0.1784, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.266537676590194, "learning_rate": 1.1794719300847493e-05, "loss": 0.1887, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2859975144551638, "learning_rate": 1.1743176509734582e-05, "loss": 0.1645, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2771320270730395, "learning_rate": 1.1691699739962275e-05, "loss": 0.1717, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.28395359960600663, "learning_rate": 1.1640289403137456e-05, "loss": 0.1702, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.28297253163738517, "learning_rate": 1.1588945910335802e-05, "loss": 0.1578, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.28592530759281015, "learning_rate": 1.1537669672098517e-05, "loss": 0.1887, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.26494323969345784, "learning_rate": 1.1486461098429036e-05, "loss": 0.1875, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.2774622613829085, "learning_rate": 1.1435320598789747e-05, "loss": 0.1801, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.26669253890218986, "learning_rate": 1.1384248582098736e-05, "loss": 0.1681, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.2616316809471135, "learning_rate": 1.1333245456726467e-05, "loss": 0.1694, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2788182133833308, "learning_rate": 1.128231163049258e-05, "loss": 0.1791, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2695724611634956, "learning_rate": 1.123144751066259e-05, "loss": 0.1732, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.29072384288615793, "learning_rate": 1.1180653503944657e-05, "loss": 0.1811, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.2916074575547321, "learning_rate": 1.1129930016486287e-05, "loss": 0.1793, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2623179590992783, "learning_rate": 1.107927745387114e-05, "loss": 0.1668, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.2791764722134958, "learning_rate": 1.1028696221115766e-05, "loss": 0.1786, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.27777099641035835, "learning_rate": 1.0978186722666341e-05, "loss": 0.1693, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.2864732310322729, "learning_rate": 1.0927749362395475e-05, "loss": 0.1699, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.270765522581885, "learning_rate": 1.0877384543598954e-05, "loss": 0.1742, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2851611607038776, "learning_rate": 1.0827092668992529e-05, "loss": 0.184, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.27032398274714114, "learning_rate": 1.077687414070869e-05, "loss": 0.1808, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.260751105757401, "learning_rate": 1.0726729360293451e-05, "loss": 0.1762, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.26721710395491444, "learning_rate": 1.0676658728703147e-05, "loss": 0.1636, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.28458058986754325, "learning_rate": 1.0626662646301198e-05, "loss": 0.1825, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2775768807946075, "learning_rate": 1.0576741512854958e-05, "loss": 0.1692, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2826152069850493, "learning_rate": 1.052689572753247e-05, "loss": 0.1746, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.27724365979965127, "learning_rate": 1.0477125688899328e-05, "loss": 0.1985, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.29396080612464537, "learning_rate": 1.0427431794915406e-05, "loss": 0.1755, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.285937782380666, "learning_rate": 1.0377814442931769e-05, "loss": 0.1895, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2702100726884872, "learning_rate": 1.0328274029687439e-05, "loss": 0.1717, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2746686761997511, "learning_rate": 1.0278810951306253e-05, "loss": 0.1576, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.28859773562272173, "learning_rate": 1.0229425603293647e-05, "loss": 0.1956, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.2800488806505022, "learning_rate": 1.0180118380533558e-05, "loss": 0.1681, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.26926274588231536, "learning_rate": 1.0130889677285225e-05, "loss": 0.1931, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.2750484313924764, "learning_rate": 1.008173988718005e-05, "loss": 0.159, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2677496221220704, "learning_rate": 1.0032669403218439e-05, "loss": 0.1664, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.26833634696505326, "learning_rate": 9.983678617766677e-06, "loss": 0.1641, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2674576663301263, "learning_rate": 9.934767922553788e-06, "loss": 0.1747, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2869927740535152, "learning_rate": 9.885937708668371e-06, "loss": 0.171, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.2681284720174686, "learning_rate": 9.837188366555524e-06, "loss": 0.1812, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.2613854690310581, "learning_rate": 9.788520286013691e-06, "loss": 0.1983, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2862251428894139, "learning_rate": 9.739933856191537e-06, "loss": 0.1835, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.28217837381098493, "learning_rate": 9.691429465584866e-06, "loss": 0.1761, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.2752995031932707, "learning_rate": 9.643007502033492e-06, "loss": 0.1907, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.27904452597769597, "learning_rate": 9.594668352718152e-06, "loss": 0.1812, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.3008309103478633, "learning_rate": 9.546412404157383e-06, "loss": 0.1687, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.2715471353548716, "learning_rate": 9.498240042204471e-06, "loss": 0.1736, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.28558449518293016, "learning_rate": 9.450151652044339e-06, "loss": 0.1484, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.27456740180406436, "learning_rate": 9.402147618190472e-06, "loss": 0.1747, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.27336683718285676, "learning_rate": 9.354228324481841e-06, "loss": 0.1615, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.26650961825916597, "learning_rate": 9.306394154079852e-06, "loss": 0.1719, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.27864137071827116, "learning_rate": 9.258645489465254e-06, "loss": 0.165, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.26806198264018577, "learning_rate": 9.21098271243509e-06, "loss": 0.1632, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.26439052409286945, "learning_rate": 9.163406204099659e-06, "loss": 0.182, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.2830131466419766, "learning_rate": 9.115916344879452e-06, "loss": 0.1631, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.28506134487620527, "learning_rate": 9.068513514502126e-06, "loss": 0.1447, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2849167797683812, "learning_rate": 9.021198091999439e-06, "loss": 0.1627, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.25636231220572453, "learning_rate": 8.973970455704251e-06, "loss": 0.1963, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.26785436987147015, "learning_rate": 8.926830983247495e-06, "loss": 0.1589, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2792647095434404, "learning_rate": 8.879780051555116e-06, "loss": 0.1626, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2848350235672856, "learning_rate": 8.83281803684512e-06, "loss": 0.1828, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.28222527138245385, "learning_rate": 8.785945314624532e-06, "loss": 0.1508, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.2664485870710499, "learning_rate": 8.739162259686385e-06, "loss": 0.1793, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2680520321299538, "learning_rate": 8.692469246106734e-06, "loss": 0.155, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.285210501729012, "learning_rate": 8.645866647241677e-06, "loss": 0.184, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2703690850452954, "learning_rate": 8.599354835724348e-06, "loss": 0.1642, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2636597374649875, "learning_rate": 8.552934183461958e-06, "loss": 0.1631, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2617007705968107, "learning_rate": 8.506605061632805e-06, "loss": 0.1502, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.26774367771425567, "learning_rate": 8.460367840683308e-06, "loss": 0.1586, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2617987498057335, "learning_rate": 8.414222890325065e-06, "loss": 0.1637, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2728020311574086, "learning_rate": 8.368170579531855e-06, "loss": 0.1752, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.2710454852535648, "learning_rate": 8.322211276536733e-06, "loss": 0.1592, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.2747624181917186, "learning_rate": 8.27634534882907e-06, "loss": 0.1685, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.25253848783369476, "learning_rate": 8.230573163151585e-06, "loss": 0.1779, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.2723077172280557, "learning_rate": 8.184895085497466e-06, "loss": 0.1754, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.27151023311976313, "learning_rate": 8.139311481107401e-06, "loss": 0.175, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.2661780177649144, "learning_rate": 8.093822714466686e-06, "loss": 0.1601, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.274709809745714, "learning_rate": 8.048429149302271e-06, "loss": 0.1704, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2602623028212477, "learning_rate": 8.003131148579902e-06, "loss": 0.172, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2555465418132496, "learning_rate": 7.957929074501182e-06, "loss": 0.1685, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.2514995624751217, "learning_rate": 7.912823288500695e-06, "loss": 0.1668, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.2542193748553816, "learning_rate": 7.867814151243102e-06, "loss": 0.182, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2739509589891697, "learning_rate": 7.822902022620267e-06, "loss": 0.1569, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.25686860300316283, "learning_rate": 7.778087261748377e-06, "loss": 0.1756, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.2591320571139797, "learning_rate": 7.733370226965056e-06, "loss": 0.1597, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.25742298892812115, "learning_rate": 7.688751275826527e-06, "loss": 0.1783, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.26606760274485275, "learning_rate": 7.644230765104735e-06, "loss": 0.1774, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.27589574283835516, "learning_rate": 7.599809050784502e-06, "loss": 0.1523, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2721583730896594, "learning_rate": 7.555486488060661e-06, "loss": 0.1656, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2705545617098703, "learning_rate": 7.511263431335249e-06, "loss": 0.163, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.25556158772079324, "learning_rate": 7.467140234214656e-06, "loss": 0.1868, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.27617497559899, "learning_rate": 7.423117249506777e-06, "loss": 0.1883, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.25701667567048825, "learning_rate": 7.379194829218231e-06, "loss": 0.1849, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.25687920283931714, "learning_rate": 7.335373324551518e-06, "loss": 0.1755, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.25628735622860854, "learning_rate": 7.291653085902224e-06, "loss": 0.1592, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2703929465924286, "learning_rate": 7.248034462856213e-06, "loss": 0.1558, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2644217761074795, "learning_rate": 7.20451780418683e-06, "loss": 0.1654, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.25996899095811116, "learning_rate": 7.161103457852128e-06, "loss": 0.1687, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.27404804904884283, "learning_rate": 7.117791770992046e-06, "loss": 0.179, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.26572787281661686, "learning_rate": 7.074583089925688e-06, "loss": 0.1684, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.26137427786591705, "learning_rate": 7.0314777601485155e-06, "loss": 0.1731, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.26528303354790567, "learning_rate": 6.988476126329604e-06, "loss": 0.1433, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.2595205613988417, "learning_rate": 6.945578532308857e-06, "loss": 0.1755, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.28095578891434786, "learning_rate": 6.902785321094301e-06, "loss": 0.1748, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.2726072499247216, "learning_rate": 6.8600968348593115e-06, "loss": 0.1785, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2584891373497948, "learning_rate": 6.817513414939892e-06, "loss": 0.1811, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.2587918377177988, "learning_rate": 6.775035401831924e-06, "loss": 0.1536, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.27768582511890094, "learning_rate": 6.732663135188473e-06, "loss": 0.1682, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.2600773802818304, "learning_rate": 6.690396953817055e-06, "loss": 0.1806, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.2510147543893157, "learning_rate": 6.648237195676927e-06, "loss": 0.1998, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.26342394612624837, "learning_rate": 6.606184197876395e-06, "loss": 0.1562, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.27536990312862325, "learning_rate": 6.564238296670109e-06, "loss": 0.1853, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2635793685636917, "learning_rate": 6.52239982745638e-06, "loss": 0.1663, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.2794764140455409, "learning_rate": 6.480669124774484e-06, "loss": 0.1807, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.27437030373595545, "learning_rate": 6.439046522302013e-06, "loss": 0.1578, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.28257840493474806, "learning_rate": 6.397532352852191e-06, "loss": 0.1881, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.24680981808304686, "learning_rate": 6.356126948371202e-06, "loss": 0.1814, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.27319565291250597, "learning_rate": 6.314830639935559e-06, "loss": 0.1436, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2676718433068564, "learning_rate": 6.273643757749448e-06, "loss": 0.1694, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.2807700744514192, "learning_rate": 6.2325666311420856e-06, "loss": 0.1526, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2688079485068071, "learning_rate": 6.1915995885650675e-06, "loss": 0.168, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.26196234546811314, "learning_rate": 6.150742957589784e-06, "loss": 0.1698, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2551748290538585, "learning_rate": 6.109997064904774e-06, "loss": 0.1863, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2568213359130851, "learning_rate": 6.069362236313092e-06, "loss": 0.1809, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.25895518664020883, "learning_rate": 6.0288387967297565e-06, "loss": 0.167, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.26069320725663503, "learning_rate": 5.988427070179108e-06, "loss": 0.1707, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.26944239726224667, "learning_rate": 5.948127379792234e-06, "loss": 0.1698, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.25111448577869, "learning_rate": 5.90794004780439e-06, "loss": 0.1672, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.25113775970070057, "learning_rate": 5.867865395552405e-06, "loss": 0.146, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.259886668023666, "learning_rate": 5.8279037434721364e-06, "loss": 0.1599, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.26544015925190634, "learning_rate": 5.788055411095892e-06, "loss": 0.19, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.26458897781091706, "learning_rate": 5.7483207170498625e-06, "loss": 0.1674, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.2608624095741764, "learning_rate": 5.708699979051613e-06, "loss": 0.1723, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.26008245368692884, "learning_rate": 5.66919351390751e-06, "loss": 0.1742, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.2478052395343173, "learning_rate": 5.629801637510188e-06, "loss": 0.172, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.26274936054056997, "learning_rate": 5.590524664836043e-06, "loss": 0.1665, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.25646905039926454, "learning_rate": 5.551362909942708e-06, "loss": 0.1477, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.23770019858409264, "learning_rate": 5.51231668596653e-06, "loss": 0.1742, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.25006369098861136, "learning_rate": 5.47338630512007e-06, "loss": 0.1691, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.25929527609119574, "learning_rate": 5.434572078689617e-06, "loss": 0.1647, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.2603028464928225, "learning_rate": 5.395874317032694e-06, "loss": 0.1905, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.25349067556101074, "learning_rate": 5.357293329575573e-06, "loss": 0.1524, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.24582364903409587, "learning_rate": 5.318829424810797e-06, "loss": 0.1664, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.2545342247845898, "learning_rate": 5.280482910294728e-06, "loss": 0.1427, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.2616679435926895, "learning_rate": 5.242254092645078e-06, "loss": 0.1707, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2504164612151124, "learning_rate": 5.2041432775384445e-06, "loss": 0.174, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.26285718680296616, "learning_rate": 5.166150769707892e-06, "loss": 0.1782, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.2572770962384334, "learning_rate": 5.128276872940503e-06, "loss": 0.1792, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.24233071434240297, "learning_rate": 5.090521890074953e-06, "loss": 0.1822, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2507544979580647, "learning_rate": 5.0528861229990675e-06, "loss": 0.1691, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.2505811282149004, "learning_rate": 5.015369872647442e-06, "loss": 0.1424, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2560505565373175, "learning_rate": 4.9779734389990195e-06, "loss": 0.1715, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.24697471514274097, "learning_rate": 4.940697121074675e-06, "loss": 0.1617, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.26093659342903375, "learning_rate": 4.903541216934864e-06, "loss": 0.1764, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.24638052669182192, "learning_rate": 4.8665060236772e-06, "loss": 0.1694, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2449271476694116, "learning_rate": 4.829591837434102e-06, "loss": 0.1658, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.2436504201851833, "learning_rate": 4.792798953370424e-06, "loss": 0.165, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.25346800911888845, "learning_rate": 4.756127665681083e-06, "loss": 0.1795, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2529138638295202, "learning_rate": 4.719578267588725e-06, "loss": 0.1758, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.24462499943624477, "learning_rate": 4.6831510513413525e-06, "loss": 0.1823, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3323040175795234, "learning_rate": 4.6468463082100176e-06, "loss": 0.1489, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.29080946726330326, "learning_rate": 4.610664328486485e-06, "loss": 0.1257, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.23366356734684926, "learning_rate": 4.5746054014809e-06, "loss": 0.1489, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.2264620273663394, "learning_rate": 4.5386698155194766e-06, "loss": 0.1519, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.2497252867554259, "learning_rate": 4.502857857942204e-06, "loss": 0.1156, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.32265002986021946, "learning_rate": 4.467169815100549e-06, "loss": 0.1521, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3011683446301388, "learning_rate": 4.431605972355137e-06, "loss": 0.1344, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.26183974190968723, "learning_rate": 4.396166614073516e-06, "loss": 0.1247, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.23455576249897056, "learning_rate": 4.360852023627846e-06, "loss": 0.126, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.26334525922631585, "learning_rate": 4.325662483392656e-06, "loss": 0.1177, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2654681976046674, "learning_rate": 4.29059827474257e-06, "loss": 0.1213, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.24737757947578784, "learning_rate": 4.255659678050063e-06, "loss": 0.1295, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.24492520807932455, "learning_rate": 4.22084697268323e-06, "loss": 0.1076, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.23594304217190293, "learning_rate": 4.186160437003535e-06, "loss": 0.1287, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.22681584515844486, "learning_rate": 4.151600348363582e-06, "loss": 0.1292, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.2290691365959507, "learning_rate": 4.11716698310493e-06, "loss": 0.114, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.22816890687865982, "learning_rate": 4.082860616555848e-06, "loss": 0.1207, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.22709911052736767, "learning_rate": 4.048681523029125e-06, "loss": 0.1228, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.26252432125526176, "learning_rate": 4.014629975819882e-06, "loss": 0.1106, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.2400622520600372, "learning_rate": 3.9807062472033855e-06, "loss": 0.1361, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2162118636750537, "learning_rate": 3.94691060843287e-06, "loss": 0.1413, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.21742925502121363, "learning_rate": 3.913243329737353e-06, "loss": 0.1084, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.24525119933546913, "learning_rate": 3.879704680319503e-06, "loss": 0.1373, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2219129983111216, "learning_rate": 3.846294928353471e-06, "loss": 0.1302, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.21980130884354515, "learning_rate": 3.8130143409827345e-06, "loss": 0.1154, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.22302685815116868, "learning_rate": 3.7798631843179887e-06, "loss": 0.1206, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2157626236094761, "learning_rate": 3.7468417234349973e-06, "loss": 0.1565, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.22093679866423774, "learning_rate": 3.7139502223724823e-06, "loss": 0.1388, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.20850348563044457, "learning_rate": 3.6811889441300095e-06, "loss": 0.1264, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.21748426579656285, "learning_rate": 3.648558150665886e-06, "loss": 0.1207, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.22157502041650773, "learning_rate": 3.616058102895075e-06, "loss": 0.1046, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2194825676069909, "learning_rate": 3.583689060687079e-06, "loss": 0.1308, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.21612781989535682, "learning_rate": 3.5514512828639023e-06, "loss": 0.1188, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.21674800525305637, "learning_rate": 3.51934502719796e-06, "loss": 0.1351, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.20583536229836016, "learning_rate": 3.4873705504100185e-06, "loss": 0.1718, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.2075841057749346, "learning_rate": 3.4555281081671345e-06, "loss": 0.1189, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.21624739821444994, "learning_rate": 3.4238179550806326e-06, "loss": 0.1167, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.209526050061856, "learning_rate": 3.3922403447040497e-06, "loss": 0.1386, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.21314655809007133, "learning_rate": 3.3607955295311247e-06, "loss": 0.1549, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.21367957764300938, "learning_rate": 3.32948376099375e-06, "loss": 0.1279, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.21789280770888625, "learning_rate": 3.2983052894599976e-06, "loss": 0.1242, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.21409194239792048, "learning_rate": 3.2672603642320945e-06, "loss": 0.1435, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.20496239169009986, "learning_rate": 3.236349233544438e-06, "loss": 0.1314, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2241190706196363, "learning_rate": 3.205572144561604e-06, "loss": 0.1292, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.23527482181684173, "learning_rate": 3.174929343376374e-06, "loss": 0.1302, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2122627492569873, "learning_rate": 3.1444210750077777e-06, "loss": 0.113, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.21904069470180323, "learning_rate": 3.1140475833991046e-06, "loss": 0.115, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.20496746969699584, "learning_rate": 3.0838091114159895e-06, "loss": 0.1344, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.20795874090934544, "learning_rate": 3.0537059008444524e-06, "loss": 0.1281, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.21536075903945665, "learning_rate": 3.0237381923889563e-06, "loss": 0.1381, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.2179748255364977, "learning_rate": 2.9939062256704997e-06, "loss": 0.1207, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.21641891789083856, "learning_rate": 2.964210239224696e-06, "loss": 0.1447, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.2174817399318629, "learning_rate": 2.934650470499869e-06, "loss": 0.1243, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2050843536712428, "learning_rate": 2.905227155855128e-06, "loss": 0.141, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.21468123946858036, "learning_rate": 2.875940530558519e-06, "loss": 0.1225, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2035758565040564, "learning_rate": 2.8467908287851154e-06, "loss": 0.137, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.2156646097874217, "learning_rate": 2.8177782836151603e-06, "loss": 0.1531, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2179096021618744, "learning_rate": 2.7889031270321874e-06, "loss": 0.1058, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2030596725522616, "learning_rate": 2.760165589921184e-06, "loss": 0.1126, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.21585904908931525, "learning_rate": 2.7315659020667305e-06, "loss": 0.1269, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21344496661033235, "learning_rate": 2.703104292151164e-06, "loss": 0.1508, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.20850129444500912, "learning_rate": 2.6747809877527607e-06, "loss": 0.1323, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.21420417725101784, "learning_rate": 2.6465962153439082e-06, "loss": 0.1263, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.21560316891663805, "learning_rate": 2.618550200289303e-06, "loss": 0.1275, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.20695497067722488, "learning_rate": 2.59064316684412e-06, "loss": 0.1321, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.21283104110752094, "learning_rate": 2.562875338152264e-06, "loss": 0.1294, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.22398783347707907, "learning_rate": 2.5352469362445552e-06, "loss": 0.1134, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.21411934792795173, "learning_rate": 2.5077581820369523e-06, "loss": 0.1136, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.20445624335934007, "learning_rate": 2.480409295328803e-06, "loss": 0.1485, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.281916726931244, "learning_rate": 2.45320049480108e-06, "loss": 0.1076, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.20769243642040425, "learning_rate": 2.4261319980146293e-06, "loss": 0.1373, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.2203208763511439, "learning_rate": 2.399204021408421e-06, "loss": 0.1256, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.2131012612867762, "learning_rate": 2.3724167802978395e-06, "loss": 0.1371, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.2160959262730134, "learning_rate": 2.3457704888729625e-06, "loss": 0.1338, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.2065700587445008, "learning_rate": 2.3192653601968162e-06, "loss": 0.1443, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.2175760835146298, "learning_rate": 2.2929016062037057e-06, "loss": 0.1256, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2069279335199892, "learning_rate": 2.2666794376975055e-06, "loss": 0.1481, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2133507274810355, "learning_rate": 2.24059906434998e-06, "loss": 0.1302, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.2181178018046262, "learning_rate": 2.214660694699091e-06, "loss": 0.1461, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.21575937973357429, "learning_rate": 2.188864536147355e-06, "loss": 0.1175, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2169758924084823, "learning_rate": 2.1632107949601757e-06, "loss": 0.1244, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.212814066042155, "learning_rate": 2.137699676264171e-06, "loss": 0.1357, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.21175919084866798, "learning_rate": 2.1123313840455738e-06, "loss": 0.1214, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.211539377215663, "learning_rate": 2.08710612114857e-06, "loss": 0.135, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2086507508864174, "learning_rate": 2.0620240892736953e-06, "loss": 0.1169, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.2174187817334202, "learning_rate": 2.0370854889762e-06, "loss": 0.1534, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.21547030905746967, "learning_rate": 2.0122905196644726e-06, "loss": 0.1284, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21138275182976943, "learning_rate": 1.987639379598427e-06, "loss": 0.1216, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21177079314771946, "learning_rate": 1.963132265887919e-06, "loss": 0.1339, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20262421116163154, "learning_rate": 1.9387693744911784e-06, "loss": 0.1045, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.21799644668556906, "learning_rate": 1.9145509002132368e-06, "loss": 0.1254, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.21417597686084397, "learning_rate": 1.8904770367043723e-06, "loss": 0.1162, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.20576375486343113, "learning_rate": 1.8665479764585504e-06, "loss": 0.127, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2259578879004506, "learning_rate": 1.8427639108118977e-06, "loss": 0.1394, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.20996342245724853, "learning_rate": 1.8191250299411755e-06, "loss": 0.1107, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.21556246081087937, "learning_rate": 1.7956315228622446e-06, "loss": 0.1269, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2094637120109721, "learning_rate": 1.7722835774285553e-06, "loss": 0.1349, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.21504271634825015, "learning_rate": 1.7490813803296624e-06, "loss": 0.1293, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.20838274249625005, "learning_rate": 1.726025117089718e-06, "loss": 0.142, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2114638017421447, "learning_rate": 1.70311497206598e-06, "loss": 0.1421, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.20534914404316687, "learning_rate": 1.6803511284473638e-06, "loss": 0.113, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.21257019659401782, "learning_rate": 1.6577337682529538e-06, "loss": 0.129, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.20218949036374884, "learning_rate": 1.6352630723305617e-06, "loss": 0.1362, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2118752556290184, "learning_rate": 1.612939220355272e-06, "loss": 0.1365, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.2260782741275512, "learning_rate": 1.5907623908280112e-06, "loss": 0.1286, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2235538289983004, "learning_rate": 1.568732761074121e-06, "loss": 0.1166, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.21025404139635628, "learning_rate": 1.5468505072419237e-06, "loss": 0.1297, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.20275499907664699, "learning_rate": 1.5251158043013448e-06, "loss": 0.1371, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.21022297922188735, "learning_rate": 1.5035288260424885e-06, "loss": 0.1285, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.21402899636706585, "learning_rate": 1.4820897450742623e-06, "loss": 0.1347, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2096769672628439, "learning_rate": 1.4607987328229767e-06, "loss": 0.1352, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.21236923545512162, "learning_rate": 1.4396559595310056e-06, "loss": 0.1276, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.1994636861504497, "learning_rate": 1.4186615942553973e-06, "loss": 0.1482, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.21288698877173695, "learning_rate": 1.3978158048665424e-06, "loss": 0.1323, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.20972691148751135, "learning_rate": 1.3771187580468115e-06, "loss": 0.1215, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.20943764693308536, "learning_rate": 1.3565706192892392e-06, "loss": 0.1313, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.2094030229507162, "learning_rate": 1.3361715528961993e-06, "loss": 0.1137, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.24031010022345456, "learning_rate": 1.3159217219780817e-06, "loss": 0.1107, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.21116893995790406, "learning_rate": 1.2958212884519949e-06, "loss": 0.1208, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.22092601269358972, "learning_rate": 1.2758704130404675e-06, "loss": 0.1417, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.2155637929915231, "learning_rate": 1.2560692552701738e-06, "loss": 0.1522, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.21166396831325363, "learning_rate": 1.2364179734706382e-06, "loss": 0.1068, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.21446692249934293, "learning_rate": 1.2169167247729852e-06, "loss": 0.1113, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2226525203191058, "learning_rate": 1.1975656651086864e-06, "loss": 0.1256, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.21516890738843777, "learning_rate": 1.1783649492082926e-06, "loss": 0.1117, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.20711132802722537, "learning_rate": 1.1593147306002183e-06, "loss": 0.1151, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.20961080680384941, "learning_rate": 1.140415161609505e-06, "loss": 0.1262, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.22141029596267103, "learning_rate": 1.121666393356604e-06, "loss": 0.1083, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2156849023792721, "learning_rate": 1.1030685757561632e-06, "loss": 0.1237, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2223187097862443, "learning_rate": 1.0846218575158373e-06, "loss": 0.1243, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.21392652826964492, "learning_rate": 1.066326386135097e-06, "loss": 0.1304, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.21494315231722017, "learning_rate": 1.0481823079040398e-06, "loss": 0.1153, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.21055881293087159, "learning_rate": 1.0301897679022344e-06, "loss": 0.1299, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.21909672777210784, "learning_rate": 1.0123489099975491e-06, "loss": 0.1263, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2023169345964207, "learning_rate": 9.9465987684501e-07, "loss": 0.1221, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.20252215816454608, "learning_rate": 9.771228098856534e-07, "loss": 0.1275, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.21118851328416274, "learning_rate": 9.597378493454013e-07, "loss": 0.1483, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.21499430533038938, "learning_rate": 9.425051342339353e-07, "loss": 0.1106, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.21462986248139374, "learning_rate": 9.254248023435864e-07, "loss": 0.1538, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.2084449334851254, "learning_rate": 9.084969902482288e-07, "loss": 0.143, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.20762491336632355, "learning_rate": 8.917218333021993e-07, "loss": 0.1101, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2139328224217312, "learning_rate": 8.750994656392109e-07, "loss": 0.1178, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.22058570010471537, "learning_rate": 8.58630020171265e-07, "loss": 0.1396, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.21158898301024884, "learning_rate": 8.423136285876099e-07, "loss": 0.1126, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2088418566784464, "learning_rate": 8.26150421353682e-07, "loss": 0.127, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.211035700996495, "learning_rate": 8.101405277100549e-07, "loss": 0.119, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.20275427106211105, "learning_rate": 7.942840756714077e-07, "loss": 0.1241, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.20286903478606605, "learning_rate": 7.785811920255093e-07, "loss": 0.1266, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.21018136279821328, "learning_rate": 7.630320023322024e-07, "loss": 0.1239, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.21127880829494236, "learning_rate": 7.476366309223903e-07, "loss": 0.1304, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.20674163862753459, "learning_rate": 7.323952008970537e-07, "loss": 0.1129, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.21479551327262097, "learning_rate": 7.173078341262618e-07, "loss": 0.1306, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.20696818868585062, "learning_rate": 7.023746512481989e-07, "loss": 0.1277, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.20740279912891219, "learning_rate": 6.875957716681902e-07, "loss": 0.1316, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.21624338030761264, "learning_rate": 6.729713135577687e-07, "loss": 0.1339, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.20788864352394995, "learning_rate": 6.585013938537143e-07, "loss": 0.1084, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.21256543276493817, "learning_rate": 6.441861282571115e-07, "loss": 0.1231, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.20434256262894884, "learning_rate": 6.300256312324471e-07, "loss": 0.1188, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2115491565108273, "learning_rate": 6.160200160066776e-07, "loss": 0.1371, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.21431418419430392, "learning_rate": 6.021693945683327e-07, "loss": 0.1396, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.2201563991038159, "learning_rate": 5.884738776666044e-07, "loss": 0.1278, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.2081182106424089, "learning_rate": 5.749335748104878e-07, "loss": 0.1318, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.2185106402950934, "learning_rate": 5.615485942678778e-07, "loss": 0.1183, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.2184517294840666, "learning_rate": 5.483190430647289e-07, "loss": 0.1488, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.21089749220032963, "learning_rate": 5.352450269841747e-07, "loss": 0.1219, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.20969476630852132, "learning_rate": 5.22326650565701e-07, "loss": 0.119, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.20756020297527214, "learning_rate": 5.095640171043048e-07, "loss": 0.1218, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.2027728120646501, "learning_rate": 4.969572286496594e-07, "loss": 0.1064, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.20957075374755302, "learning_rate": 4.845063860053079e-07, "loss": 0.1198, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2016406360613623, "learning_rate": 4.7221158872785997e-07, "loss": 0.1239, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.21242537914217616, "learning_rate": 4.600729351261857e-07, "loss": 0.1302, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.20160525403536117, "learning_rate": 4.4809052226063355e-07, "loss": 0.1435, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.2076013891997975, "learning_rate": 4.3626444594226046e-07, "loss": 0.1148, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2174246123055893, "learning_rate": 4.245948007320588e-07, "loss": 0.1203, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.20685512511588502, "learning_rate": 4.130816799401971e-07, "loss": 0.1059, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.20467456565735026, "learning_rate": 4.017251756252827e-07, "loss": 0.1454, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.20618037567616787, "learning_rate": 3.9052537859362473e-07, "loss": 0.1274, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.21174538461655604, "learning_rate": 3.7948237839849687e-07, "loss": 0.1302, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.21714295958771587, "learning_rate": 3.6859626333943797e-07, "loss": 0.1246, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.21718769528831003, "learning_rate": 3.578671204615347e-07, "loss": 0.1142, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.21735113634225725, "learning_rate": 3.472950355547267e-07, "loss": 0.1031, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.20784975305266046, "learning_rate": 3.3688009315312244e-07, "loss": 0.1259, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.20762858994254474, "learning_rate": 3.266223765343224e-07, "loss": 0.1351, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.20627831242940972, "learning_rate": 3.16521967718757e-07, "loss": 0.11, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.21052437341202687, "learning_rate": 3.0657894746902726e-07, "loss": 0.1226, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.20676889485022376, "learning_rate": 2.9679339528925654e-07, "loss": 0.1573, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.21336058142443048, "learning_rate": 2.871653894244597e-07, "loss": 0.1173, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2157338744736078, "learning_rate": 2.7769500685991266e-07, "loss": 0.1308, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2141111906641719, "learning_rate": 2.683823233205485e-07, "loss": 0.1339, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.20331986047685635, "learning_rate": 2.592274132703287e-07, "loss": 0.1144, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.21264504258755793, "learning_rate": 2.502303499116754e-07, "loss": 0.1029, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.21142682412562677, "learning_rate": 2.413912051848666e-07, "loss": 0.1293, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.20485983162088955, "learning_rate": 2.3271004976746613e-07, "loss": 0.1339, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2050930848182874, "learning_rate": 2.2418695307376393e-07, "loss": 0.1438, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2066412518896554, "learning_rate": 2.1582198325420968e-07, "loss": 0.1185, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.21093752818037334, "learning_rate": 2.0761520719488447e-07, "loss": 0.1373, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.20467402677809401, "learning_rate": 1.9956669051694798e-07, "loss": 0.1444, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.21763719654157304, "learning_rate": 1.916764975761254e-07, "loss": 0.1319, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.203933833987773, "learning_rate": 1.839446914621923e-07, "loss": 0.1413, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.21544443761004498, "learning_rate": 1.7637133399845962e-07, "loss": 0.1151, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.21225603377579494, "learning_rate": 1.6895648574129397e-07, "loss": 0.1315, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2075125564539864, "learning_rate": 1.6170020597962465e-07, "loss": 0.137, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.22512440259010022, "learning_rate": 1.5460255273447078e-07, "loss": 0.1278, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.20928992635741117, "learning_rate": 1.4766358275847715e-07, "loss": 0.1228, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.21871129450642143, "learning_rate": 1.4088335153546573e-07, "loss": 0.1416, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.20589683564074565, "learning_rate": 1.3426191327998496e-07, "loss": 0.1553, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.21196067698536206, "learning_rate": 1.277993209368744e-07, "loss": 0.1256, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.20908995973303152, "learning_rate": 1.214956261808542e-07, "loss": 0.1251, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.2116862717750233, "learning_rate": 1.1535087941609846e-07, "loss": 0.124, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.19640506246558703, "learning_rate": 1.0936512977583802e-07, "loss": 0.1347, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.2070873711017827, "learning_rate": 1.0353842512196732e-07, "loss": 0.1435, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.20446861032356306, "learning_rate": 9.787081204466253e-08, "loss": 0.1353, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2189698497237059, "learning_rate": 9.236233586200627e-08, "loss": 0.118, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.20913973110395234, "learning_rate": 8.70130406196279e-08, "loss": 0.1492, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2070099602303538, "learning_rate": 8.182296909035047e-08, "loss": 0.1132, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.20162492758166897, "learning_rate": 7.679216277384439e-08, "loss": 0.1471, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.20838783248591392, "learning_rate": 7.19206618963053e-08, "loss": 0.1395, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.1988221054815047, "learning_rate": 6.720850541012347e-08, "loss": 0.1249, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.20455680531983184, "learning_rate": 6.265573099357714e-08, "loss": 0.1352, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.20589458028787214, "learning_rate": 5.826237505053067e-08, "loss": 0.1475, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.20696676864146996, "learning_rate": 5.4028472710137e-08, "loss": 0.1434, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.20471756020569498, "learning_rate": 4.9954057826571146e-08, "loss": 0.1234, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.20355857418840817, "learning_rate": 4.6039162978743776e-08, "loss": 0.1327, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.21652998249192157, "learning_rate": 4.228381947004812e-08, "loss": 0.1309, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.21324357442719727, "learning_rate": 3.868805732811343e-08, "loss": 0.0992, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.21241766678561164, "learning_rate": 3.525190530455636e-08, "loss": 0.1259, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.20169977550862658, "learning_rate": 3.197539087475887e-08, "loss": 0.1209, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2107740382716963, "learning_rate": 2.8858540237641786e-08, "loss": 0.1132, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.21098815426193646, "learning_rate": 2.5901378315458247e-08, "loss": 0.1214, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.197294374014009, "learning_rate": 2.3103928753598347e-08, "loss": 0.1072, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.20334620046892715, "learning_rate": 2.0466213920393718e-08, "loss": 0.1208, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.2110042664240134, "learning_rate": 1.7988254906942115e-08, "loss": 0.1145, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.22797811901563578, "learning_rate": 1.5670071526936447e-08, "loss": 0.1248, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.20963734315731536, "learning_rate": 1.3511682316509344e-08, "loss": 0.1123, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.21085660390095, "learning_rate": 1.1513104534086605e-08, "loss": 0.1238, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.20242542663357502, "learning_rate": 9.67435416023843e-09, "loss": 0.1244, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.21172600229719357, "learning_rate": 7.995445897566178e-09, "loss": 0.124, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.20110944481818094, "learning_rate": 6.476393170578021e-09, "loss": 0.1157, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.2109196917227294, "learning_rate": 5.11720812557348e-09, "loss": 0.1224, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.20365422621669366, "learning_rate": 3.917901630563492e-09, "loss": 0.1155, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.20265649104980157, "learning_rate": 2.878483275170485e-09, "loss": 0.1141, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.20661761563842854, "learning_rate": 1.998961370555108e-09, "loss": 0.1114, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.21144287803368292, "learning_rate": 1.2793429493518361e-09, "loss": 0.1184, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2033580062152246, "learning_rate": 7.196337656112384e-10, "loss": 0.1192, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.20191875233304266, "learning_rate": 3.198382947511292e-10, "loss": 0.124, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.2124035882000412, "learning_rate": 7.995973352770137e-11, "loss": 0.132, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.2013777669216394, "learning_rate": 0.0, "loss": 0.1328, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.8600293763309896e+18, "train_loss": 0.2672070719030222, "train_runtime": 23060.9507, "train_samples_per_second": 6.851, "train_steps_per_second": 0.054 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.8600293763309896e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }