{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 6.7736415382545205, "learning_rate": 3.2258064516129035e-07, "loss": 1.0985, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.629327828267507, "learning_rate": 6.451612903225807e-07, "loss": 1.0795, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.761807409403573, "learning_rate": 9.67741935483871e-07, "loss": 1.0721, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.49605796529749, "learning_rate": 1.2903225806451614e-06, "loss": 1.0813, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.189468372042714, "learning_rate": 1.6129032258064516e-06, "loss": 1.0724, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.077088205151075, "learning_rate": 1.935483870967742e-06, "loss": 1.0459, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.126762408138897, "learning_rate": 2.2580645161290324e-06, "loss": 1.0108, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.721032020141449, "learning_rate": 2.580645161290323e-06, "loss": 1.021, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.598146902191028, "learning_rate": 2.903225806451613e-06, "loss": 0.9444, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.446232762663463, "learning_rate": 3.225806451612903e-06, "loss": 0.9342, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.1793332861934265, "learning_rate": 3.548387096774194e-06, "loss": 0.9385, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.405376404186286, "learning_rate": 3.870967741935484e-06, "loss": 0.964, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.545319697954825, "learning_rate": 4.193548387096774e-06, "loss": 0.9503, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.505155990286561, "learning_rate": 4.516129032258065e-06, "loss": 0.9242, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.127391673942952, "learning_rate": 4.838709677419355e-06, "loss": 0.9092, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.021292556402506, "learning_rate": 5.161290322580646e-06, "loss": 0.8549, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.9428477538688598, "learning_rate": 5.483870967741935e-06, "loss": 0.8521, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.5590881064342392, "learning_rate": 5.806451612903226e-06, "loss": 0.8203, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.3156655605551735, "learning_rate": 6.129032258064517e-06, "loss": 0.8497, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 2.07805678312517, "learning_rate": 6.451612903225806e-06, "loss": 0.8506, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.6678782445626874, "learning_rate": 6.774193548387097e-06, "loss": 0.8337, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.6644349181658558, "learning_rate": 7.096774193548388e-06, "loss": 0.766, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.9564656606651203, "learning_rate": 7.4193548387096784e-06, "loss": 0.7931, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.8847279552160938, "learning_rate": 7.741935483870968e-06, "loss": 0.7935, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.4392949649353235, "learning_rate": 8.064516129032258e-06, "loss": 0.7887, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.1528045049930704, "learning_rate": 8.387096774193549e-06, "loss": 0.7781, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.2225083510306698, "learning_rate": 8.70967741935484e-06, "loss": 0.766, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.2372396076835124, "learning_rate": 9.03225806451613e-06, "loss": 0.7845, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.1266667602598532, "learning_rate": 9.35483870967742e-06, "loss": 0.773, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.0759762453385588, "learning_rate": 9.67741935483871e-06, "loss": 0.7752, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.9314265575569396, "learning_rate": 1e-05, "loss": 0.7714, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.82871782016197, "learning_rate": 1.0322580645161291e-05, "loss": 0.7446, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.8253593482440141, "learning_rate": 1.0645161290322582e-05, "loss": 0.7479, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7119674937404654, "learning_rate": 1.096774193548387e-05, "loss": 0.756, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.795769150018204, "learning_rate": 1.1290322580645164e-05, "loss": 0.7773, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.7005873104832636, "learning_rate": 1.1612903225806453e-05, "loss": 0.7181, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.6291269461218403, "learning_rate": 1.1935483870967743e-05, "loss": 0.7161, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.7878722944942401, "learning_rate": 1.2258064516129034e-05, "loss": 0.721, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.6841783855391398, "learning_rate": 1.2580645161290324e-05, "loss": 0.7428, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6831326703791427, "learning_rate": 1.2903225806451613e-05, "loss": 0.7412, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7990170902123458, "learning_rate": 1.3225806451612903e-05, "loss": 0.7128, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6799564361368345, "learning_rate": 1.3548387096774194e-05, "loss": 0.7254, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.650690415921759, "learning_rate": 1.3870967741935486e-05, "loss": 0.731, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.7391069374015499, "learning_rate": 1.4193548387096776e-05, "loss": 0.7023, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6123144103214522, "learning_rate": 1.4516129032258066e-05, "loss": 0.7054, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.8308456307076098, "learning_rate": 1.4838709677419357e-05, "loss": 0.7182, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.7271125811988521, "learning_rate": 1.5161290322580646e-05, "loss": 0.7156, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.6635995916509315, "learning_rate": 1.5483870967741936e-05, "loss": 0.685, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.7562021860495868, "learning_rate": 1.5806451612903226e-05, "loss": 0.7186, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.7630028088601661, "learning_rate": 1.6129032258064517e-05, "loss": 0.6919, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.7645016237415292, "learning_rate": 1.6451612903225807e-05, "loss": 0.6819, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.9261609931710906, "learning_rate": 1.6774193548387098e-05, "loss": 0.6999, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.7268171383197236, "learning_rate": 1.7096774193548388e-05, "loss": 0.686, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.8924562942045354, "learning_rate": 1.741935483870968e-05, "loss": 0.6828, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7860900167184134, "learning_rate": 1.774193548387097e-05, "loss": 0.689, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 1.060337460924545, "learning_rate": 1.806451612903226e-05, "loss": 0.6957, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.712503207598713, "learning_rate": 1.838709677419355e-05, "loss": 0.6933, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.8655406098837405, "learning_rate": 1.870967741935484e-05, "loss": 0.684, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.779913675846795, "learning_rate": 1.903225806451613e-05, "loss": 0.6889, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.7653344061036312, "learning_rate": 1.935483870967742e-05, "loss": 0.6641, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.7697400061779711, "learning_rate": 1.967741935483871e-05, "loss": 0.6583, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.7071777678528192, "learning_rate": 2e-05, "loss": 0.6722, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.7087818742720909, "learning_rate": 2.0322580645161292e-05, "loss": 0.6696, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 1.040020886296081, "learning_rate": 2.0645161290322582e-05, "loss": 0.6936, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.8414512312591435, "learning_rate": 2.0967741935483873e-05, "loss": 0.6717, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.8894606839986281, "learning_rate": 2.1290322580645163e-05, "loss": 0.6557, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.6828252791603057, "learning_rate": 2.161290322580645e-05, "loss": 0.6668, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.9030483632694458, "learning_rate": 2.193548387096774e-05, "loss": 0.6644, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.6601879955848787, "learning_rate": 2.225806451612903e-05, "loss": 0.6712, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.7985854437974906, "learning_rate": 2.2580645161290328e-05, "loss": 0.6528, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7279015476707607, "learning_rate": 2.2903225806451615e-05, "loss": 0.6652, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7648164889579782, "learning_rate": 2.3225806451612906e-05, "loss": 0.6809, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.7812890154751206, "learning_rate": 2.3548387096774196e-05, "loss": 0.6652, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.814190665163826, "learning_rate": 2.3870967741935486e-05, "loss": 0.7062, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 1.0004400115955157, "learning_rate": 2.4193548387096777e-05, "loss": 0.6708, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.722399009180003, "learning_rate": 2.4516129032258067e-05, "loss": 0.6598, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.7989867265831112, "learning_rate": 2.4838709677419358e-05, "loss": 0.6554, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.9186153488313114, "learning_rate": 2.5161290322580648e-05, "loss": 0.6622, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7103409637949343, "learning_rate": 2.548387096774194e-05, "loss": 0.672, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.1316076469650587, "learning_rate": 2.5806451612903226e-05, "loss": 0.6514, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.7556985117118392, "learning_rate": 2.6129032258064516e-05, "loss": 0.6705, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.0336431744069128, "learning_rate": 2.6451612903225806e-05, "loss": 0.6676, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8698072840425453, "learning_rate": 2.6774193548387097e-05, "loss": 0.6738, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.8964797685943583, "learning_rate": 2.7096774193548387e-05, "loss": 0.6523, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.8972792359126518, "learning_rate": 2.7419354838709678e-05, "loss": 0.6768, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7701018335441296, "learning_rate": 2.774193548387097e-05, "loss": 0.6854, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.818998825965113, "learning_rate": 2.8064516129032262e-05, "loss": 0.6482, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.8636677083756634, "learning_rate": 2.8387096774193552e-05, "loss": 0.6718, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.9538445428563967, "learning_rate": 2.8709677419354843e-05, "loss": 0.6363, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7442909778479593, "learning_rate": 2.9032258064516133e-05, "loss": 0.6705, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.6886014010960088, "learning_rate": 2.9354838709677423e-05, "loss": 0.6586, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.7656724981695366, "learning_rate": 2.9677419354838714e-05, "loss": 0.666, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.7088857544053644, "learning_rate": 3.0000000000000004e-05, "loss": 0.6481, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7479929940319131, "learning_rate": 3.032258064516129e-05, "loss": 0.6565, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.8269841021520538, "learning_rate": 3.0645161290322585e-05, "loss": 0.6504, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.6828047178678928, "learning_rate": 3.096774193548387e-05, "loss": 0.6592, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.9047002042793114, "learning_rate": 3.1290322580645166e-05, "loss": 0.6353, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.9624729181387609, "learning_rate": 3.161290322580645e-05, "loss": 0.6399, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.7832413366936066, "learning_rate": 3.193548387096774e-05, "loss": 0.6663, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.9239755346893215, "learning_rate": 3.2258064516129034e-05, "loss": 0.6653, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.785027713651937, "learning_rate": 3.258064516129033e-05, "loss": 0.6451, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.9002043881161633, "learning_rate": 3.2903225806451614e-05, "loss": 0.6515, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.7165638100707247, "learning_rate": 3.322580645161291e-05, "loss": 0.6708, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.2897209678217414, "learning_rate": 3.3548387096774195e-05, "loss": 0.6524, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.7689368689944, "learning_rate": 3.387096774193549e-05, "loss": 0.6707, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.0698620137352246, "learning_rate": 3.4193548387096776e-05, "loss": 0.6377, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.8016253613095073, "learning_rate": 3.451612903225807e-05, "loss": 0.6334, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.8743644707293605, "learning_rate": 3.483870967741936e-05, "loss": 0.6529, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.8861743494049965, "learning_rate": 3.516129032258065e-05, "loss": 0.6475, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.8172146644890349, "learning_rate": 3.548387096774194e-05, "loss": 0.6661, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.6538181321245606, "learning_rate": 3.5806451612903225e-05, "loss": 0.6391, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8686247202529443, "learning_rate": 3.612903225806452e-05, "loss": 0.6559, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.7172359279130719, "learning_rate": 3.6451612903225805e-05, "loss": 0.6484, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.8209455552404661, "learning_rate": 3.67741935483871e-05, "loss": 0.6349, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.713045485239202, "learning_rate": 3.7096774193548386e-05, "loss": 0.6457, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.7587412385984931, "learning_rate": 3.741935483870968e-05, "loss": 0.6462, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.750209430989415, "learning_rate": 3.7741935483870974e-05, "loss": 0.6626, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.6648274343892279, "learning_rate": 3.806451612903226e-05, "loss": 0.618, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.7435950544396973, "learning_rate": 3.8387096774193555e-05, "loss": 0.6615, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.759824888467019, "learning_rate": 3.870967741935484e-05, "loss": 0.6058, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.703909900686409, "learning_rate": 3.9032258064516135e-05, "loss": 0.6277, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.9761382716629834, "learning_rate": 3.935483870967742e-05, "loss": 0.6768, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.8018007511677644, "learning_rate": 3.9677419354838716e-05, "loss": 0.6434, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.9539666941443571, "learning_rate": 4e-05, "loss": 0.6264, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.8451831097149393, "learning_rate": 3.9999920040266474e-05, "loss": 0.6216, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.7508466128775725, "learning_rate": 3.999968016170525e-05, "loss": 0.6348, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.8965284462518867, "learning_rate": 3.9999280366234394e-05, "loss": 0.661, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.9911541892838767, "learning_rate": 3.999872065705065e-05, "loss": 0.6466, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.740633739268415, "learning_rate": 3.999800103862945e-05, "loss": 0.6484, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.8707119293372457, "learning_rate": 3.9997121516724834e-05, "loss": 0.6465, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.8291970635744659, "learning_rate": 3.999608209836944e-05, "loss": 0.6305, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.877795748867918, "learning_rate": 3.999488279187443e-05, "loss": 0.6566, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.7833554145591265, "learning_rate": 3.9993523606829425e-05, "loss": 0.6215, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7753867904761621, "learning_rate": 3.9992004554102435e-05, "loss": 0.6708, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7560419604311167, "learning_rate": 3.999032564583976e-05, "loss": 0.6225, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.6870883745133399, "learning_rate": 3.998848689546591e-05, "loss": 0.6201, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.6528725971215578, "learning_rate": 3.9986488317683496e-05, "loss": 0.6432, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.6742636273557107, "learning_rate": 3.9984329928473067e-05, "loss": 0.618, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.6426421786107445, "learning_rate": 3.998201174509306e-05, "loss": 0.6265, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.5757313211130346, "learning_rate": 3.997953378607961e-05, "loss": 0.6131, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6524771351453621, "learning_rate": 3.9976896071246403e-05, "loss": 0.6298, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.6198487392595052, "learning_rate": 3.997409862168454e-05, "loss": 0.671, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.680633844119908, "learning_rate": 3.997114145976237e-05, "loss": 0.6503, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.6794994232589542, "learning_rate": 3.9968024609125245e-05, "loss": 0.6486, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.5845512550848941, "learning_rate": 3.996474809469545e-05, "loss": 0.6408, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.671633251685232, "learning_rate": 3.996131194267189e-05, "loss": 0.6328, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.8494824635310019, "learning_rate": 3.995771618052995e-05, "loss": 0.6419, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.7880049060232076, "learning_rate": 3.9953960837021256e-05, "loss": 0.6258, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7182637736559427, "learning_rate": 3.995004594217343e-05, "loss": 0.6374, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7486641802687933, "learning_rate": 3.994597152728987e-05, "loss": 0.6111, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6379675718488914, "learning_rate": 3.994173762494947e-05, "loss": 0.6322, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6447401511428792, "learning_rate": 3.9937344269006424e-05, "loss": 0.6323, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.6502580407125356, "learning_rate": 3.993279149458988e-05, "loss": 0.6439, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.5840149434173686, "learning_rate": 3.9928079338103695e-05, "loss": 0.6295, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.655963417250298, "learning_rate": 3.992320783722616e-05, "loss": 0.6157, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.6427114654355139, "learning_rate": 3.991817703090965e-05, "loss": 0.6274, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6098661623581284, "learning_rate": 3.991298695938038e-05, "loss": 0.6418, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6763069443292848, "learning_rate": 3.9907637664138e-05, "loss": 0.6503, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6413546084729741, "learning_rate": 3.990212918795534e-05, "loss": 0.6525, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.6410988910673017, "learning_rate": 3.9896461574878036e-05, "loss": 0.6384, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6159036493531032, "learning_rate": 3.989063487022416e-05, "loss": 0.6495, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.6117982240774149, "learning_rate": 3.9884649120583903e-05, "loss": 0.6074, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5288780567410826, "learning_rate": 3.987850437381915e-05, "loss": 0.6193, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6948700375290562, "learning_rate": 3.987220067906313e-05, "loss": 0.6505, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.6227260563264463, "learning_rate": 3.986573808672002e-05, "loss": 0.6576, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6260059473672833, "learning_rate": 3.9859116648464534e-05, "loss": 0.6341, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.6359362573046372, "learning_rate": 3.985233641724152e-05, "loss": 0.6566, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.5871222826014774, "learning_rate": 3.984539744726554e-05, "loss": 0.6403, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6100293718800532, "learning_rate": 3.983829979402038e-05, "loss": 0.6611, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.719367474937541, "learning_rate": 3.983104351425871e-05, "loss": 0.6467, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6575022336383567, "learning_rate": 3.982362866600154e-05, "loss": 0.6434, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.7496864601161931, "learning_rate": 3.9816055308537806e-05, "loss": 0.627, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.5596895248503375, "learning_rate": 3.980832350242388e-05, "loss": 0.6424, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.58841435717063, "learning_rate": 3.980043330948306e-05, "loss": 0.6348, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.583782572094908, "learning_rate": 3.9792384792805124e-05, "loss": 0.6394, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5781446415566823, "learning_rate": 3.978417801674579e-05, "loss": 0.616, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.5682816352053428, "learning_rate": 3.9775813046926244e-05, "loss": 0.6244, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6067568755032914, "learning_rate": 3.976728995023254e-05, "loss": 0.6427, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.5744663438102103, "learning_rate": 3.975860879481514e-05, "loss": 0.6097, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.6186235913925572, "learning_rate": 3.974976965008833e-05, "loss": 0.6129, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5507896166512573, "learning_rate": 3.9740772586729674e-05, "loss": 0.6043, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.6101904716391157, "learning_rate": 3.973161767667946e-05, "loss": 0.6139, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.5217014611479655, "learning_rate": 3.972230499314009e-05, "loss": 0.5963, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.5916074083817112, "learning_rate": 3.9712834610575545e-05, "loss": 0.6142, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5740810700225029, "learning_rate": 3.9703206604710746e-05, "loss": 0.6297, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.5748089053432356, "learning_rate": 3.969342105253098e-05, "loss": 0.6072, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6307039674723393, "learning_rate": 3.9683478032281246e-05, "loss": 0.6053, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5987767077773676, "learning_rate": 3.967337762346568e-05, "loss": 0.6204, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.6946491647634624, "learning_rate": 3.9663119906846885e-05, "loss": 0.6098, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5915721946030811, "learning_rate": 3.965270496444528e-05, "loss": 0.6151, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6212606486878469, "learning_rate": 3.9642132879538465e-05, "loss": 0.6052, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5601078718434955, "learning_rate": 3.9631403736660566e-05, "loss": 0.5878, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5547355252080635, "learning_rate": 3.962051762160151e-05, "loss": 0.6249, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.5800963968266929, "learning_rate": 3.960947462140638e-05, "loss": 0.6217, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5665073582210889, "learning_rate": 3.959827482437472e-05, "loss": 0.6087, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.6334837025295241, "learning_rate": 3.958691832005981e-05, "loss": 0.617, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5698426328233831, "learning_rate": 3.9575405199267944e-05, "loss": 0.6253, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.650034422201678, "learning_rate": 3.956373555405774e-05, "loss": 0.6079, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6133183109140116, "learning_rate": 3.955190947773937e-05, "loss": 0.6266, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.62973550975677, "learning_rate": 3.9539927064873824e-05, "loss": 0.6163, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6890988358345805, "learning_rate": 3.952778841127214e-05, "loss": 0.6173, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5766739242396232, "learning_rate": 3.95154936139947e-05, "loss": 0.5961, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.7276969489011441, "learning_rate": 3.950304277135034e-05, "loss": 0.5936, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.5982724316351082, "learning_rate": 3.94904359828957e-05, "loss": 0.6248, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.6431600551598374, "learning_rate": 3.94776733494343e-05, "loss": 0.6107, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.6083394951194204, "learning_rate": 3.9464754973015826e-05, "loss": 0.5982, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5602683395836091, "learning_rate": 3.9451680956935275e-05, "loss": 0.6347, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5115577461453824, "learning_rate": 3.943845140573213e-05, "loss": 0.6048, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.6500097576337421, "learning_rate": 3.942506642518952e-05, "loss": 0.6158, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.6054741196247154, "learning_rate": 3.9411526122333396e-05, "loss": 0.6223, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.5819488358297142, "learning_rate": 3.939783060543167e-05, "loss": 0.6155, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.737008970720981, "learning_rate": 3.938397998399333e-05, "loss": 0.5911, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6506677337303446, "learning_rate": 3.936997436876756e-05, "loss": 0.6202, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6249986483432605, "learning_rate": 3.935581387174289e-05, "loss": 0.6006, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5790190463092336, "learning_rate": 3.9341498606146295e-05, "loss": 0.6021, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.6051082732362986, "learning_rate": 3.932702868644224e-05, "loss": 0.6177, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5615517830708069, "learning_rate": 3.931240422833181e-05, "loss": 0.625, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5894837496933347, "learning_rate": 3.9297625348751806e-05, "loss": 0.5823, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5455094628651538, "learning_rate": 3.9282692165873744e-05, "loss": 0.5845, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.540221293709415, "learning_rate": 3.9267604799102945e-05, "loss": 0.6065, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.6054454448306223, "learning_rate": 3.9252363369077615e-05, "loss": 0.6005, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5734266522661706, "learning_rate": 3.9236967997667796e-05, "loss": 0.5846, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.74057815875644, "learning_rate": 3.9221418807974496e-05, "loss": 0.6006, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5820193403908613, "learning_rate": 3.92057159243286e-05, "loss": 0.6158, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.6111942023701544, "learning_rate": 3.9189859472289956e-05, "loss": 0.5898, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.47098573050959863, "learning_rate": 3.9173849578646324e-05, "loss": 0.6029, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6038799906632983, "learning_rate": 3.9157686371412395e-05, "loss": 0.6014, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5336419584820936, "learning_rate": 3.914136997982874e-05, "loss": 0.6029, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5127845856097313, "learning_rate": 3.912490053436079e-05, "loss": 0.6237, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5232604771273117, "learning_rate": 3.9108278166697805e-05, "loss": 0.6124, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5198025369015625, "learning_rate": 3.909150300975178e-05, "loss": 0.6155, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4932083707955771, "learning_rate": 3.907457519765642e-05, "loss": 0.5927, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5642261466084997, "learning_rate": 3.905749486576607e-05, "loss": 0.6247, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.5760051418965967, "learning_rate": 3.90402621506546e-05, "loss": 0.6319, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5931731186484825, "learning_rate": 3.902287719011435e-05, "loss": 0.5961, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.5272093052040966, "learning_rate": 3.900534012315499e-05, "loss": 0.6015, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5389850309836416, "learning_rate": 3.8987651090002454e-05, "loss": 0.5797, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.505728562616951, "learning_rate": 3.896981023209777e-05, "loss": 0.6041, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.5726165214255362, "learning_rate": 3.8951817692095966e-05, "loss": 0.5714, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5383873160864292, "learning_rate": 3.893367361386491e-05, "loss": 0.6085, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.5689514961278475, "learning_rate": 3.891537814248417e-05, "loss": 0.5769, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.5199263037994082, "learning_rate": 3.889693142424384e-05, "loss": 0.5852, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5002401007929582, "learning_rate": 3.8878333606643405e-05, "loss": 0.609, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.5574092981328239, "learning_rate": 3.885958483839049e-05, "loss": 0.6095, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.708024086773553, "learning_rate": 3.8840685269399786e-05, "loss": 0.5985, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.4822992662294965, "learning_rate": 3.882163505079171e-05, "loss": 0.5881, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5324616212876133, "learning_rate": 3.880243433489132e-05, "loss": 0.581, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.6424709173124262, "learning_rate": 3.878308327522702e-05, "loss": 0.4903, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.5208371462778842, "learning_rate": 3.876358202652936e-05, "loss": 0.4773, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.6516978645498337, "learning_rate": 3.8743930744729835e-05, "loss": 0.4872, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.604072226701365, "learning_rate": 3.8724129586959535e-05, "loss": 0.4924, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.6209011658392406, "learning_rate": 3.870417871154801e-05, "loss": 0.4745, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6688692757164981, "learning_rate": 3.868407827802192e-05, "loss": 0.5029, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5463221482956419, "learning_rate": 3.8663828447103804e-05, "loss": 0.4982, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.696561312895444, "learning_rate": 3.8643429380710765e-05, "loss": 0.4861, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6000101737934399, "learning_rate": 3.862288124195319e-05, "loss": 0.4904, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.7441878773846925, "learning_rate": 3.8602184195133464e-05, "loss": 0.4857, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.8128946986676217, "learning_rate": 3.8581338405744604e-05, "loss": 0.48, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.5361940983990593, "learning_rate": 3.8560344040468996e-05, "loss": 0.4909, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.6563075448583118, "learning_rate": 3.853920126717703e-05, "loss": 0.4821, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5651579268465933, "learning_rate": 3.851791025492574e-05, "loss": 0.4794, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.6480432404150303, "learning_rate": 3.8496471173957515e-05, "loss": 0.4746, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.6560907169801582, "learning_rate": 3.847488419569866e-05, "loss": 0.4985, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.49181905965396794, "learning_rate": 3.8453149492758077e-05, "loss": 0.469, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6141572884275026, "learning_rate": 3.8431267238925886e-05, "loss": 0.4978, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5164241818329539, "learning_rate": 3.840923760917199e-05, "loss": 0.4724, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.6436894240639434, "learning_rate": 3.838706077964473e-05, "loss": 0.4845, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.5511818473016342, "learning_rate": 3.836473692766944e-05, "loss": 0.4965, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5883196575248287, "learning_rate": 3.834226623174705e-05, "loss": 0.4708, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.499368230743349, "learning_rate": 3.831964887155264e-05, "loss": 0.4875, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6205229821119359, "learning_rate": 3.829688502793403e-05, "loss": 0.4787, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5204778179361711, "learning_rate": 3.827397488291029e-05, "loss": 0.5094, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.5833020384431518, "learning_rate": 3.8250918619670343e-05, "loss": 0.4728, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5444170306923645, "learning_rate": 3.822771642257145e-05, "loss": 0.4949, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5554986297769653, "learning_rate": 3.820436847713776e-05, "loss": 0.4633, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.5484917317552315, "learning_rate": 3.8180874970058826e-05, "loss": 0.4783, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5177684341257802, "learning_rate": 3.8157236089188103e-05, "loss": 0.4722, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.5669133768130457, "learning_rate": 3.813345202354145e-05, "loss": 0.4622, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.7195367674572277, "learning_rate": 3.810952296329563e-05, "loss": 0.4748, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.6564054350677714, "learning_rate": 3.808544909978676e-05, "loss": 0.4663, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.5174605800566396, "learning_rate": 3.806123062550882e-05, "loss": 0.4807, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.6885074783159604, "learning_rate": 3.803686773411208e-05, "loss": 0.4713, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.5201393672560176, "learning_rate": 3.801236062040158e-05, "loss": 0.5026, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.917736204028884, "learning_rate": 3.798770948033553e-05, "loss": 0.4901, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5233883502600546, "learning_rate": 3.796291451102381e-05, "loss": 0.4678, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.8562494852915854, "learning_rate": 3.793797591072631e-05, "loss": 0.4944, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6353049875921224, "learning_rate": 3.791289387885144e-05, "loss": 0.4899, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.6400700800236869, "learning_rate": 3.788766861595443e-05, "loss": 0.4917, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.6432365346184166, "learning_rate": 3.7862300323735835e-05, "loss": 0.4891, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.6248777011209772, "learning_rate": 3.783678920503983e-05, "loss": 0.4975, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.5664665861722579, "learning_rate": 3.781113546385265e-05, "loss": 0.4871, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.6096682213206334, "learning_rate": 3.7785339305300916e-05, "loss": 0.4979, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5559044163987239, "learning_rate": 3.7759400935650025e-05, "loss": 0.5084, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.6208199512153443, "learning_rate": 3.77333205623025e-05, "loss": 0.4691, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.5263289905802299, "learning_rate": 3.7707098393796295e-05, "loss": 0.4798, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.6657182636764423, "learning_rate": 3.7680734639803185e-05, "loss": 0.5023, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.535431389987428, "learning_rate": 3.765422951112704e-05, "loss": 0.5032, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.537868070080345, "learning_rate": 3.762758321970216e-05, "loss": 0.4815, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.5924751929268375, "learning_rate": 3.7600795978591584e-05, "loss": 0.4841, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.513570448694745, "learning_rate": 3.757386800198538e-05, "loss": 0.4932, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.5682651759934428, "learning_rate": 3.7546799505198925e-05, "loss": 0.4929, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5654505719395633, "learning_rate": 3.7519590704671197e-05, "loss": 0.4713, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5061638533028103, "learning_rate": 3.749224181796305e-05, "loss": 0.4899, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.6556359967882811, "learning_rate": 3.746475306375545e-05, "loss": 0.5136, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.4456214677580402, "learning_rate": 3.743712466184774e-05, "loss": 0.4795, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.5855628507504966, "learning_rate": 3.7409356833155885e-05, "loss": 0.475, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4982074295388911, "learning_rate": 3.73814497997107e-05, "loss": 0.4913, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.5704862806182162, "learning_rate": 3.7353403784656095e-05, "loss": 0.4852, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5145485159937843, "learning_rate": 3.732521901224724e-05, "loss": 0.4879, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.539352621260021, "learning_rate": 3.7296895707848844e-05, "loss": 0.4685, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.5303907097267774, "learning_rate": 3.7268434097933275e-05, "loss": 0.4931, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.5273966450169993, "learning_rate": 3.723983441007882e-05, "loss": 0.5023, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5791468105937103, "learning_rate": 3.721109687296781e-05, "loss": 0.4822, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.5224846767466135, "learning_rate": 3.718222171638484e-05, "loss": 0.5027, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.6247360077806232, "learning_rate": 3.715320917121488e-05, "loss": 0.5029, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.495256627339395, "learning_rate": 3.712405946944149e-05, "loss": 0.4707, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.5632805019778911, "learning_rate": 3.709477284414488e-05, "loss": 0.4759, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.5554933087810779, "learning_rate": 3.7065349529500136e-05, "loss": 0.4917, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.5761546547119941, "learning_rate": 3.7035789760775305e-05, "loss": 0.5, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.5422092063102915, "learning_rate": 3.70060937743295e-05, "loss": 0.469, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.5950053974135762, "learning_rate": 3.6976261807611045e-05, "loss": 0.4744, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.6761453363245188, "learning_rate": 3.694629409915555e-05, "loss": 0.5065, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6011922443341084, "learning_rate": 3.691619088858401e-05, "loss": 0.499, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5223715494996036, "learning_rate": 3.68859524166009e-05, "loss": 0.4648, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.6700692306113929, "learning_rate": 3.6855578924992226e-05, "loss": 0.4925, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.533397916364554, "learning_rate": 3.6825070656623626e-05, "loss": 0.4945, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.557297478945495, "learning_rate": 3.67944278554384e-05, "loss": 0.4845, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.614506516285163, "learning_rate": 3.676365076645557e-05, "loss": 0.4896, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.5451426818467114, "learning_rate": 3.673273963576791e-05, "loss": 0.4908, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.5961221899953366, "learning_rate": 3.670169471054001e-05, "loss": 0.4664, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.5990148137110534, "learning_rate": 3.6670516239006254e-05, "loss": 0.4861, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.582431685697135, "learning_rate": 3.663920447046888e-05, "loss": 0.4904, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.5831850449894824, "learning_rate": 3.6607759655295954e-05, "loss": 0.4942, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5716173336221532, "learning_rate": 3.657618204491937e-05, "loss": 0.4773, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.5454015440250742, "learning_rate": 3.6544471891832875e-05, "loss": 0.4934, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.45368315373693147, "learning_rate": 3.6512629449589983e-05, "loss": 0.49, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.5400854820137729, "learning_rate": 3.6480654972802045e-05, "loss": 0.483, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.49980256216410157, "learning_rate": 3.644854871713611e-05, "loss": 0.4975, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.5027620809156313, "learning_rate": 3.6416310939312924e-05, "loss": 0.4892, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.5368375157087747, "learning_rate": 3.638394189710493e-05, "loss": 0.4779, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.5755204426602359, "learning_rate": 3.635144184933412e-05, "loss": 0.497, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.5334385305886683, "learning_rate": 3.6318811055869994e-05, "loss": 0.5364, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.5335122711938002, "learning_rate": 3.628604977762752e-05, "loss": 0.4578, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.511994144111283, "learning_rate": 3.6253158276565004e-05, "loss": 0.4941, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5588207571668506, "learning_rate": 3.6220136815682016e-05, "loss": 0.5137, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.5347623197097484, "learning_rate": 3.618698565901727e-05, "loss": 0.4915, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.5921746049573269, "learning_rate": 3.615370507164654e-05, "loss": 0.4892, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5254868041909733, "learning_rate": 3.61202953196805e-05, "loss": 0.4915, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5685074929311719, "learning_rate": 3.6086756670262654e-05, "loss": 0.4652, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4604152430837169, "learning_rate": 3.6053089391567135e-05, "loss": 0.4774, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.5691122649054238, "learning_rate": 3.601929375279662e-05, "loss": 0.4819, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.6095445501270912, "learning_rate": 3.598537002418012e-05, "loss": 0.4847, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.53347363321611, "learning_rate": 3.5951318476970885e-05, "loss": 0.5102, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5052740600801982, "learning_rate": 3.591713938344416e-05, "loss": 0.4856, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.6545722860694612, "learning_rate": 3.588283301689507e-05, "loss": 0.48, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.5166212700591223, "learning_rate": 3.5848399651636424e-05, "loss": 0.4731, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.6784104851633385, "learning_rate": 3.5813839562996473e-05, "loss": 0.4643, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5134989517333156, "learning_rate": 3.5779153027316775e-05, "loss": 0.4744, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.6130646514925668, "learning_rate": 3.574434032194994e-05, "loss": 0.487, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.5369434626424449, "learning_rate": 3.5709401725257436e-05, "loss": 0.5068, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4987950072405776, "learning_rate": 3.5674337516607346e-05, "loss": 0.4771, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.52040387957774, "learning_rate": 3.563914797637216e-05, "loss": 0.5014, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5061520177357284, "learning_rate": 3.560383338592649e-05, "loss": 0.4855, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5302297590164625, "learning_rate": 3.556839402764487e-05, "loss": 0.4752, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.47810948055462155, "learning_rate": 3.553283018489946e-05, "loss": 0.4722, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5178212303016858, "learning_rate": 3.54971421420578e-05, "loss": 0.4727, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5022215864329299, "learning_rate": 3.5461330184480524e-05, "loss": 0.4849, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.46746345013512736, "learning_rate": 3.54253945985191e-05, "loss": 0.4876, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.496212037415295, "learning_rate": 3.5389335671513524e-05, "loss": 0.4848, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.48182982539049507, "learning_rate": 3.5353153691789986e-05, "loss": 0.4827, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.5354127762116007, "learning_rate": 3.531684894865866e-05, "loss": 0.4951, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5971023757021469, "learning_rate": 3.528042173241128e-05, "loss": 0.4922, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4932573833737516, "learning_rate": 3.524387233431892e-05, "loss": 0.4624, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.5842873566140463, "learning_rate": 3.520720104662958e-05, "loss": 0.5045, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.480394593895757, "learning_rate": 3.5170408162565904e-05, "loss": 0.5018, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.5517433146425765, "learning_rate": 3.513349397632281e-05, "loss": 0.4793, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4856094502327181, "learning_rate": 3.5096458783065145e-05, "loss": 0.4784, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.506000093286599, "learning_rate": 3.505930287892533e-05, "loss": 0.4773, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.4586392830307233, "learning_rate": 3.502202656100099e-05, "loss": 0.4906, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.4444333389893846, "learning_rate": 3.498463012735256e-05, "loss": 0.4835, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.44641140354197617, "learning_rate": 3.494711387700094e-05, "loss": 0.474, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.5101056545572663, "learning_rate": 3.490947810992505e-05, "loss": 0.4966, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.5534387512983681, "learning_rate": 3.48717231270595e-05, "loss": 0.4758, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4757242035388023, "learning_rate": 3.483384923029211e-05, "loss": 0.4875, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.5050179929356676, "learning_rate": 3.479585672246156e-05, "loss": 0.4905, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.5231474832225965, "learning_rate": 3.4757745907354924e-05, "loss": 0.4861, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.5581069698281252, "learning_rate": 3.471951708970527e-05, "loss": 0.4779, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4739858882492857, "learning_rate": 3.468117057518921e-05, "loss": 0.4753, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.6016074024305643, "learning_rate": 3.4642706670424426e-05, "loss": 0.4939, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.5194877636392149, "learning_rate": 3.460412568296731e-05, "loss": 0.4845, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.5259216764438854, "learning_rate": 3.456542792131039e-05, "loss": 0.4875, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.5139662788402773, "learning_rate": 3.4526613694879936e-05, "loss": 0.4716, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.5042540577428989, "learning_rate": 3.448768331403348e-05, "loss": 0.4764, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.4189196888118404, "learning_rate": 3.44486370900573e-05, "loss": 0.4822, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.5437822409053934, "learning_rate": 3.440947533516396e-05, "loss": 0.4827, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.45866593990574306, "learning_rate": 3.4370198362489816e-05, "loss": 0.4915, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.5031953133490108, "learning_rate": 3.43308064860925e-05, "loss": 0.5115, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.4893461862913784, "learning_rate": 3.4291300020948393e-05, "loss": 0.4854, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.44267039962047244, "learning_rate": 3.425167928295015e-05, "loss": 0.4748, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.4558777571779177, "learning_rate": 3.421194458890411e-05, "loss": 0.4863, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.4913032539864226, "learning_rate": 3.4172096256527865e-05, "loss": 0.4838, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.4462189710535747, "learning_rate": 3.4132134604447595e-05, "loss": 0.4975, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.5277342483564168, "learning_rate": 3.409205995219561e-05, "loss": 0.492, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.4388199648535286, "learning_rate": 3.4051872620207765e-05, "loss": 0.4949, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.520405673041293, "learning_rate": 3.40115729298209e-05, "loss": 0.4952, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.5001790751086735, "learning_rate": 3.397116120327025e-05, "loss": 0.4972, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.4738080458828004, "learning_rate": 3.3930637763686916e-05, "loss": 0.4814, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.4377851031986663, "learning_rate": 3.389000293509524e-05, "loss": 0.4943, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.4640177637545707, "learning_rate": 3.3849257042410225e-05, "loss": 0.4802, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.45449707031741393, "learning_rate": 3.380840041143494e-05, "loss": 0.4767, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.478163727032403, "learning_rate": 3.376743336885792e-05, "loss": 0.4858, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.49479103314850487, "learning_rate": 3.372635624225055e-05, "loss": 0.4904, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.4588176355634665, "learning_rate": 3.3685169360064445e-05, "loss": 0.4724, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4664465056728661, "learning_rate": 3.3643873051628804e-05, "loss": 0.4895, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4384729600230696, "learning_rate": 3.3602467647147814e-05, "loss": 0.4724, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.4249903515786103, "learning_rate": 3.356095347769799e-05, "loss": 0.462, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.4762236895685129, "learning_rate": 3.351933087522552e-05, "loss": 0.4749, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.41291576197372065, "learning_rate": 3.3477600172543626e-05, "loss": 0.4571, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.4679763003865818, "learning_rate": 3.3435761703329894e-05, "loss": 0.4852, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.4270550522075592, "learning_rate": 3.3393815802123606e-05, "loss": 0.4871, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.47157609618936647, "learning_rate": 3.335176280432308e-05, "loss": 0.4757, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.46339923284185575, "learning_rate": 3.330960304618295e-05, "loss": 0.4702, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4511038406462081, "learning_rate": 3.326733686481153e-05, "loss": 0.4867, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.45995922826483226, "learning_rate": 3.3224964598168084e-05, "loss": 0.4815, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.4336991522817566, "learning_rate": 3.318248658506012e-05, "loss": 0.4899, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.435029994306949, "learning_rate": 3.313990316514069e-05, "loss": 0.482, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.447408760078067, "learning_rate": 3.309721467890571e-05, "loss": 0.4826, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.4238393505165891, "learning_rate": 3.305442146769115e-05, "loss": 0.482, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.46383952446373117, "learning_rate": 3.30115238736704e-05, "loss": 0.4838, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.4265919939214464, "learning_rate": 3.296852223985148e-05, "loss": 0.4806, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.5000030947523807, "learning_rate": 3.2925416910074315e-05, "loss": 0.5037, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.4266273198655811, "learning_rate": 3.288220822900796e-05, "loss": 0.4688, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.43569962245044824, "learning_rate": 3.283889654214788e-05, "loss": 0.4689, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.47530581431954244, "learning_rate": 3.279548219581317e-05, "loss": 0.485, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.40961621196950776, "learning_rate": 3.275196553714379e-05, "loss": 0.4678, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.4714138202864899, "learning_rate": 3.270834691409778e-05, "loss": 0.4686, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.4251563382183065, "learning_rate": 3.266462667544849e-05, "loss": 0.4867, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.494628417912956, "learning_rate": 3.262080517078178e-05, "loss": 0.5003, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.46446039979264797, "learning_rate": 3.257688275049323e-05, "loss": 0.4812, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.44136909728467955, "learning_rate": 3.253285976578535e-05, "loss": 0.5009, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.48208569059084405, "learning_rate": 3.2488736568664756e-05, "loss": 0.486, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.4360078491373524, "learning_rate": 3.244451351193935e-05, "loss": 0.4537, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.558397853908972, "learning_rate": 3.240019094921551e-05, "loss": 0.4704, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.424266375207984, "learning_rate": 3.235576923489527e-05, "loss": 0.4859, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.5683494535427144, "learning_rate": 3.2311248724173476e-05, "loss": 0.4911, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.43496909198762684, "learning_rate": 3.226662977303494e-05, "loss": 0.4835, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.5075752555717419, "learning_rate": 3.2221912738251626e-05, "loss": 0.5082, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.47759248657887426, "learning_rate": 3.2177097977379736e-05, "loss": 0.4955, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.44066628201135616, "learning_rate": 3.21321858487569e-05, "loss": 0.4725, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4707362118778135, "learning_rate": 3.208717671149931e-05, "loss": 0.4678, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.476413842142146, "learning_rate": 3.204207092549882e-05, "loss": 0.4836, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.4964401812408872, "learning_rate": 3.19968688514201e-05, "loss": 0.4689, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.4569848339513977, "learning_rate": 3.195157085069774e-05, "loss": 0.4735, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.46088381347441276, "learning_rate": 3.190617728553332e-05, "loss": 0.4816, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.432000841864007, "learning_rate": 3.1860688518892606e-05, "loss": 0.4794, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.47503511532593645, "learning_rate": 3.181510491450254e-05, "loss": 0.4961, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.5142776676059225, "learning_rate": 3.176942683684842e-05, "loss": 0.4888, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.4658432130208904, "learning_rate": 3.1723654651170934e-05, "loss": 0.461, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.47199374130079724, "learning_rate": 3.167778872346327e-05, "loss": 0.4749, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.47180988726841117, "learning_rate": 3.163182942046815e-05, "loss": 0.4821, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.4056103304490428, "learning_rate": 3.158577710967494e-05, "loss": 0.4431, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.5027124983209406, "learning_rate": 3.153963215931669e-05, "loss": 0.4632, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.4383716019653644, "learning_rate": 3.14933949383672e-05, "loss": 0.4836, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.5065316843674667, "learning_rate": 3.144706581653805e-05, "loss": 0.4743, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.429878439783726, "learning_rate": 3.140064516427566e-05, "loss": 0.464, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.47534308842130446, "learning_rate": 3.135413335275833e-05, "loss": 0.489, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.4413222730238107, "learning_rate": 3.130753075389327e-05, "loss": 0.4705, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4396217509752682, "learning_rate": 3.1260837740313625e-05, "loss": 0.4892, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.4657894441203913, "learning_rate": 3.121405468537547e-05, "loss": 0.4778, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.4315987212157068, "learning_rate": 3.116718196315488e-05, "loss": 0.4562, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.5046271720037652, "learning_rate": 3.1120219948444894e-05, "loss": 0.4838, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.47709127886611263, "learning_rate": 3.107316901675252e-05, "loss": 0.4823, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.44039037483375715, "learning_rate": 3.1026029544295745e-05, "loss": 0.4726, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.4677854346788355, "learning_rate": 3.097880190800057e-05, "loss": 0.4899, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.4831102682297353, "learning_rate": 3.093148648549788e-05, "loss": 0.4834, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.5158142626898674, "learning_rate": 3.088408365512055e-05, "loss": 0.4991, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.5303500251650827, "learning_rate": 3.083659379590034e-05, "loss": 0.5004, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.4722363304263484, "learning_rate": 3.0789017287564913e-05, "loss": 0.4751, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.5772113946189532, "learning_rate": 3.074135451053475e-05, "loss": 0.4668, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.4640425044988884, "learning_rate": 3.069360584592015e-05, "loss": 0.4751, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.5344811308486491, "learning_rate": 3.064577167551816e-05, "loss": 0.4749, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.4734268177457408, "learning_rate": 3.059785238180953e-05, "loss": 0.4814, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.4881333216972797, "learning_rate": 3.054984834795566e-05, "loss": 0.4744, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.5027910359087944, "learning_rate": 3.0501759957795537e-05, "loss": 0.4836, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.4382483144731275, "learning_rate": 3.0453587595842627e-05, "loss": 0.4645, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.5525921941960891, "learning_rate": 3.0405331647281856e-05, "loss": 0.4932, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.4699058746271588, "learning_rate": 3.0356992497966508e-05, "loss": 0.4703, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.43543907161171547, "learning_rate": 3.0308570534415137e-05, "loss": 0.4757, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.48672233538895465, "learning_rate": 3.0260066143808467e-05, "loss": 0.4821, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.42796055058215304, "learning_rate": 3.021147971398632e-05, "loss": 0.4691, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.4135962736149227, "learning_rate": 3.0162811633444478e-05, "loss": 0.4917, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.4078244703160084, "learning_rate": 3.0114062291331635e-05, "loss": 0.4595, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.43354959187441316, "learning_rate": 3.0065232077446217e-05, "loss": 0.4848, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.4351403281288951, "learning_rate": 3.001632138223332e-05, "loss": 0.4446, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.6399204007844467, "learning_rate": 2.9967330596781565e-05, "loss": 0.3302, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.5000267276231214, "learning_rate": 2.9918260112819952e-05, "loss": 0.3401, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.9077480734143463, "learning_rate": 2.9869110322714778e-05, "loss": 0.3448, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5241891786326338, "learning_rate": 2.9819881619466447e-05, "loss": 0.3669, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.5378345256181157, "learning_rate": 2.9770574396706364e-05, "loss": 0.3376, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5184411888996596, "learning_rate": 2.972118904869376e-05, "loss": 0.3383, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4631962503310879, "learning_rate": 2.9671725970312563e-05, "loss": 0.3325, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5068144685995319, "learning_rate": 2.9622185557068238e-05, "loss": 0.3307, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.4855693077992948, "learning_rate": 2.95725682050846e-05, "loss": 0.3287, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.4892622024831948, "learning_rate": 2.9522874311100684e-05, "loss": 0.3285, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.4621005256673435, "learning_rate": 2.9473104272467526e-05, "loss": 0.3686, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.49735840323715186, "learning_rate": 2.942325848714505e-05, "loss": 0.3276, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.48060198384325487, "learning_rate": 2.9373337353698804e-05, "loss": 0.3307, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4935401391516336, "learning_rate": 2.932334127129686e-05, "loss": 0.3251, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.48761254059452797, "learning_rate": 2.9273270639706547e-05, "loss": 0.3403, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.5194749840834629, "learning_rate": 2.922312585929131e-05, "loss": 0.3417, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.48539220509849607, "learning_rate": 2.9172907331007478e-05, "loss": 0.3523, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.49466645136491444, "learning_rate": 2.9122615456401053e-05, "loss": 0.3473, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.48522456233769695, "learning_rate": 2.9072250637604535e-05, "loss": 0.3298, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.4605705882347133, "learning_rate": 2.9021813277333667e-05, "loss": 0.3255, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.4957844776882589, "learning_rate": 2.8971303778884244e-05, "loss": 0.3467, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.4142827513094693, "learning_rate": 2.8920722546128863e-05, "loss": 0.3265, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.5322358677786125, "learning_rate": 2.887006998351372e-05, "loss": 0.3478, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4146416636208049, "learning_rate": 2.881934649605535e-05, "loss": 0.3427, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.46045621680144666, "learning_rate": 2.8768552489337408e-05, "loss": 0.3371, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.43402497359199543, "learning_rate": 2.8717688369507425e-05, "loss": 0.3425, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.4676405526996492, "learning_rate": 2.8666754543273535e-05, "loss": 0.3337, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4217363759085321, "learning_rate": 2.8615751417901273e-05, "loss": 0.3225, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.4577223883899878, "learning_rate": 2.856467940121025e-05, "loss": 0.3396, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.45277735564155586, "learning_rate": 2.8513538901570964e-05, "loss": 0.3411, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.45366461372964284, "learning_rate": 2.846233032790149e-05, "loss": 0.3317, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.43228247568605443, "learning_rate": 2.84110540896642e-05, "loss": 0.3337, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.47436322086428456, "learning_rate": 2.8359710596862555e-05, "loss": 0.361, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.409411967886336, "learning_rate": 2.8308300260037734e-05, "loss": 0.3235, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.495350269795955, "learning_rate": 2.8256823490265424e-05, "loss": 0.3431, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3913769753572912, "learning_rate": 2.8205280699152515e-05, "loss": 0.3271, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.5139789027607033, "learning_rate": 2.8153672298833777e-05, "loss": 0.3347, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.4106347302496501, "learning_rate": 2.8101998701968615e-05, "loss": 0.3472, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.506836606776648, "learning_rate": 2.805026032173773e-05, "loss": 0.3307, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.4001297677211304, "learning_rate": 2.7998457571839832e-05, "loss": 0.351, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.4680104465661174, "learning_rate": 2.7946590866488322e-05, "loss": 0.3338, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.42288764465380474, "learning_rate": 2.7894660620408e-05, "loss": 0.3321, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.44848756595407063, "learning_rate": 2.784266724883173e-05, "loss": 0.3335, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.4288894713403352, "learning_rate": 2.7790611167497128e-05, "loss": 0.3309, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.40948814562151986, "learning_rate": 2.7738492792643224e-05, "loss": 0.3276, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.48552745599574354, "learning_rate": 2.768631254100716e-05, "loss": 0.3119, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.4351261569126062, "learning_rate": 2.7634070829820836e-05, "loss": 0.3264, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.47313609793652317, "learning_rate": 2.7581768076807592e-05, "loss": 0.324, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.43059171817736897, "learning_rate": 2.7529404700178832e-05, "loss": 0.3172, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.4878019551675343, "learning_rate": 2.7476981118630735e-05, "loss": 0.3595, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.42682734041452813, "learning_rate": 2.742449775134085e-05, "loss": 0.3247, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.46650356924139397, "learning_rate": 2.7371955017964788e-05, "loss": 0.3452, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.42948023505636407, "learning_rate": 2.7319353338632845e-05, "loss": 0.3419, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.49542640011283084, "learning_rate": 2.7266693133946645e-05, "loss": 0.3524, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.4123654641099149, "learning_rate": 2.7213974824975785e-05, "loss": 0.311, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.514560431804867, "learning_rate": 2.7161198833254464e-05, "loss": 0.3273, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.4206203360475649, "learning_rate": 2.7108365580778095e-05, "loss": 0.3378, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.4734069810111683, "learning_rate": 2.705547548999996e-05, "loss": 0.3334, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.4789248598267234, "learning_rate": 2.7002528983827817e-05, "loss": 0.3328, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.4819857470716326, "learning_rate": 2.6949526485620517e-05, "loss": 0.3423, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.45253048705868193, "learning_rate": 2.6896468419184623e-05, "loss": 0.3266, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.501492949448831, "learning_rate": 2.6843355208771024e-05, "loss": 0.3342, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.4363511120652594, "learning_rate": 2.6790187279071536e-05, "loss": 0.3497, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.5337556015842795, "learning_rate": 2.67369650552155e-05, "loss": 0.3177, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.4225098116442984, "learning_rate": 2.6683688962766407e-05, "loss": 0.3336, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.5646304927829068, "learning_rate": 2.6630359427718468e-05, "loss": 0.3499, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.43493380534284326, "learning_rate": 2.6576976876493225e-05, "loss": 0.3419, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.5356005806348809, "learning_rate": 2.652354173593614e-05, "loss": 0.3411, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.4095521207602332, "learning_rate": 2.647005443331317e-05, "loss": 0.3418, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.4875383303692629, "learning_rate": 2.6416515396307354e-05, "loss": 0.3543, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.45504977849061584, "learning_rate": 2.636292505301542e-05, "loss": 0.3466, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.45556633814697944, "learning_rate": 2.630928383194431e-05, "loss": 0.3201, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.48344766427624725, "learning_rate": 2.625559216200781e-05, "loss": 0.3428, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5114926352444582, "learning_rate": 2.620185047252308e-05, "loss": 0.3505, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.450275556270269, "learning_rate": 2.614805919320723e-05, "loss": 0.348, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.4548577881429226, "learning_rate": 2.6094218754173895e-05, "loss": 0.3476, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.4464496113610888, "learning_rate": 2.60403295859298e-05, "loss": 0.3379, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.4312779246654216, "learning_rate": 2.5986392119371297e-05, "loss": 0.3347, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.4430425599662381, "learning_rate": 2.5932406785780928e-05, "loss": 0.3343, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.43795617622015864, "learning_rate": 2.5878374016823987e-05, "loss": 0.3273, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.4619440088760558, "learning_rate": 2.5824294244545045e-05, "loss": 0.336, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.4582462324853001, "learning_rate": 2.577016790136453e-05, "loss": 0.3346, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.42264607318506187, "learning_rate": 2.5715995420075225e-05, "loss": 0.3636, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.43970938280090954, "learning_rate": 2.5661777233838864e-05, "loss": 0.3493, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.4620397955268433, "learning_rate": 2.5607513776182616e-05, "loss": 0.3184, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.42730069308525137, "learning_rate": 2.5553205480995633e-05, "loss": 0.346, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.42329703517241335, "learning_rate": 2.5498852782525604e-05, "loss": 0.3372, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.4140384639593777, "learning_rate": 2.5444456115375252e-05, "loss": 0.3391, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.4152252179766421, "learning_rate": 2.539001591449889e-05, "loss": 0.3459, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.44470503696782293, "learning_rate": 2.53355326151989e-05, "loss": 0.3339, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.4516352436813008, "learning_rate": 2.5281006653122288e-05, "loss": 0.3294, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3853608347956877, "learning_rate": 2.5226438464257217e-05, "loss": 0.334, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.4372341255731077, "learning_rate": 2.5171828484929447e-05, "loss": 0.3515, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.39497057769974536, "learning_rate": 2.5117177151798934e-05, "loss": 0.3361, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.4351066866838664, "learning_rate": 2.506248490185627e-05, "loss": 0.3356, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.44364808502303726, "learning_rate": 2.500775217241923e-05, "loss": 0.3567, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4259343276986002, "learning_rate": 2.4952979401129266e-05, "loss": 0.3422, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.48764617121494214, "learning_rate": 2.4898167025948e-05, "loss": 0.351, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.4086874701154023, "learning_rate": 2.4843315485153703e-05, "loss": 0.3545, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.4891911050409316, "learning_rate": 2.4788425217337856e-05, "loss": 0.3527, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.423674707370151, "learning_rate": 2.4733496661401572e-05, "loss": 0.3364, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.4239540969714521, "learning_rate": 2.4678530256552114e-05, "loss": 0.3525, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.41061308010518166, "learning_rate": 2.46235264422994e-05, "loss": 0.3349, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.39332286584884196, "learning_rate": 2.4568485658452452e-05, "loss": 0.3573, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.40126223117309817, "learning_rate": 2.451340834511592e-05, "loss": 0.3481, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.42663290253898284, "learning_rate": 2.4458294942686528e-05, "loss": 0.3457, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.38820434023585837, "learning_rate": 2.440314589184958e-05, "loss": 0.3614, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.41996439337628333, "learning_rate": 2.434796163357541e-05, "loss": 0.3279, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.4081791623106512, "learning_rate": 2.429274260911588e-05, "loss": 0.338, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.42232422009924103, "learning_rate": 2.423748926000084e-05, "loss": 0.3406, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.40687058958090866, "learning_rate": 2.418220202803459e-05, "loss": 0.3353, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.4147770870658748, "learning_rate": 2.412688135529237e-05, "loss": 0.3338, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.4030558597604411, "learning_rate": 2.4071527684116807e-05, "loss": 0.3432, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.4281506505107808, "learning_rate": 2.4016141457114372e-05, "loss": 0.328, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.40835566510313975, "learning_rate": 2.396072311715187e-05, "loss": 0.3413, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.45157369257637364, "learning_rate": 2.3905273107352863e-05, "loss": 0.3372, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.430339724470913, "learning_rate": 2.3849791871094157e-05, "loss": 0.3259, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.4250708031330175, "learning_rate": 2.379427985200223e-05, "loss": 0.3512, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.4735110450660168, "learning_rate": 2.373873749394972e-05, "loss": 0.3426, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.41226150429451125, "learning_rate": 2.3683165241051836e-05, "loss": 0.3556, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.38403840205910517, "learning_rate": 2.3627563537662823e-05, "loss": 0.3221, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.42465745816597933, "learning_rate": 2.3571932828372433e-05, "loss": 0.3558, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.4551233994560646, "learning_rate": 2.351627355800233e-05, "loss": 0.3514, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.39782641589433326, "learning_rate": 2.346058617160256e-05, "loss": 0.318, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.38641886697793326, "learning_rate": 2.3404871114447976e-05, "loss": 0.3342, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.40323223152679877, "learning_rate": 2.334912883203469e-05, "loss": 0.3763, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3829319802930218, "learning_rate": 2.3293359770076505e-05, "loss": 0.3199, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.40434494399370374, "learning_rate": 2.323756437450136e-05, "loss": 0.3461, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.38669219179656694, "learning_rate": 2.3181743091447754e-05, "loss": 0.3439, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.37353290737929734, "learning_rate": 2.3125896367261164e-05, "loss": 0.3316, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.40825462301820625, "learning_rate": 2.307002464849052e-05, "loss": 0.3372, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.4007514073726155, "learning_rate": 2.30141283818846e-05, "loss": 0.3401, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3799091378879147, "learning_rate": 2.2958208014388462e-05, "loss": 0.3402, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.4293578017151091, "learning_rate": 2.2902263993139857e-05, "loss": 0.3474, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.41063377002986995, "learning_rate": 2.2846296765465708e-05, "loss": 0.3314, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.43602665234995885, "learning_rate": 2.2790306778878465e-05, "loss": 0.3428, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.4512876445986289, "learning_rate": 2.273429448107257e-05, "loss": 0.3221, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3899999895853232, "learning_rate": 2.2678260319920868e-05, "loss": 0.3366, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.39030619320498267, "learning_rate": 2.262220474347102e-05, "loss": 0.3348, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.4023636074259499, "learning_rate": 2.2566128199941918e-05, "loss": 0.3278, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.4082564232803595, "learning_rate": 2.2510031137720104e-05, "loss": 0.3627, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.454473432596326, "learning_rate": 2.2453914005356206e-05, "loss": 0.3306, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.40746841476769563, "learning_rate": 2.2397777251561302e-05, "loss": 0.3317, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.4111858833809476, "learning_rate": 2.2341621325203393e-05, "loss": 0.3393, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.41804903129058346, "learning_rate": 2.2285446675303764e-05, "loss": 0.332, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.3853556961611544, "learning_rate": 2.2229253751033423e-05, "loss": 0.3351, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.3866969441935728, "learning_rate": 2.2173043001709492e-05, "loss": 0.3248, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.40717827300754705, "learning_rate": 2.2116814876791627e-05, "loss": 0.3089, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.38074555547450667, "learning_rate": 2.2060569825878413e-05, "loss": 0.319, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.39463160727980506, "learning_rate": 2.2004308298703777e-05, "loss": 0.334, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3880160023085479, "learning_rate": 2.1948030745133396e-05, "loss": 0.3493, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.4222491723315331, "learning_rate": 2.1891737615161083e-05, "loss": 0.3261, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.365386854840674, "learning_rate": 2.1835429358905218e-05, "loss": 0.3512, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3903598730470872, "learning_rate": 2.17791064266051e-05, "loss": 0.339, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.4188597562520661, "learning_rate": 2.172276926861741e-05, "loss": 0.3462, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.3626982815380638, "learning_rate": 2.166641833541255e-05, "loss": 0.3325, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.36720033709667943, "learning_rate": 2.161005407757109e-05, "loss": 0.3291, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3769861210018528, "learning_rate": 2.155367694578013e-05, "loss": 0.3448, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.40553504077661895, "learning_rate": 2.1497287390829712e-05, "loss": 0.3443, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.37684126242132204, "learning_rate": 2.1440885863609208e-05, "loss": 0.3478, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.4242700112775347, "learning_rate": 2.1384472815103737e-05, "loss": 0.3467, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.40620105664418804, "learning_rate": 2.1328048696390534e-05, "loss": 0.3491, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.3796498798234736, "learning_rate": 2.1271613958635342e-05, "loss": 0.3309, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.39830617406508745, "learning_rate": 2.1215169053088825e-05, "loss": 0.3324, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.4181495593017284, "learning_rate": 2.1158714431082937e-05, "loss": 0.3307, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.4049108085014804, "learning_rate": 2.110225054402733e-05, "loss": 0.355, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.3922006556887935, "learning_rate": 2.1045777843405747e-05, "loss": 0.3406, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.40752417519045975, "learning_rate": 2.09892967807724e-05, "loss": 0.3326, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.4453239679970717, "learning_rate": 2.093280780774835e-05, "loss": 0.3545, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.4165108653422676, "learning_rate": 2.087631137601793e-05, "loss": 0.3476, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3842733537830768, "learning_rate": 2.0819807937325104e-05, "loss": 0.3364, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.43687627204046525, "learning_rate": 2.0763297943469847e-05, "loss": 0.3387, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.42549058548455704, "learning_rate": 2.070678184630458e-05, "loss": 0.3527, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.37634181993516697, "learning_rate": 2.06502600977305e-05, "loss": 0.3381, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.4190572529671396, "learning_rate": 2.0593733149694008e-05, "loss": 0.334, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3854213289427171, "learning_rate": 2.0537201454183074e-05, "loss": 0.3203, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.4052872531318484, "learning_rate": 2.0480665463223626e-05, "loss": 0.3429, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3986238573918953, "learning_rate": 2.042412562887594e-05, "loss": 0.3383, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.4111443360833448, "learning_rate": 2.0367582403231033e-05, "loss": 0.3369, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.4170795161263942, "learning_rate": 2.0311036238407023e-05, "loss": 0.3418, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.40638009644615214, "learning_rate": 2.0254487586545534e-05, "loss": 0.3289, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.4149943612895293, "learning_rate": 2.0197936899808088e-05, "loss": 0.3307, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3965720202604588, "learning_rate": 2.0141384630372466e-05, "loss": 0.346, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.41160748376633927, "learning_rate": 2.0084831230429106e-05, "loss": 0.3432, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.39935731641469874, "learning_rate": 2.0028277152177492e-05, "loss": 0.3415, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.37567235729639575, "learning_rate": 1.9971722847822518e-05, "loss": 0.3472, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.4209326263280301, "learning_rate": 1.99151687695709e-05, "loss": 0.3165, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.38987624506753643, "learning_rate": 1.9858615369627537e-05, "loss": 0.3206, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.44278044653017695, "learning_rate": 1.9802063100191916e-05, "loss": 0.3381, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.4233878514573154, "learning_rate": 1.974551241345447e-05, "loss": 0.3213, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.38555774316788277, "learning_rate": 1.9688963761592984e-05, "loss": 0.317, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3804235479043353, "learning_rate": 1.963241759676897e-05, "loss": 0.3354, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.40412987810962, "learning_rate": 1.9575874371124066e-05, "loss": 0.3475, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.391362474499199, "learning_rate": 1.951933453677638e-05, "loss": 0.3386, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.40860467173592396, "learning_rate": 1.9462798545816932e-05, "loss": 0.3418, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.3705935325464624, "learning_rate": 1.9406266850305996e-05, "loss": 0.3418, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.3836972684556451, "learning_rate": 1.9349739902269503e-05, "loss": 0.3484, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3875712506603039, "learning_rate": 1.9293218153695425e-05, "loss": 0.3436, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.37361362173493556, "learning_rate": 1.9236702056530153e-05, "loss": 0.3286, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.39069210097184476, "learning_rate": 1.9180192062674907e-05, "loss": 0.3324, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.3735052402359928, "learning_rate": 1.9123688623982076e-05, "loss": 0.3366, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3865181170531304, "learning_rate": 1.906719219225165e-05, "loss": 0.3272, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.39053856203394144, "learning_rate": 1.9010703219227603e-05, "loss": 0.3571, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.39234508281583097, "learning_rate": 1.8954222156594256e-05, "loss": 0.3468, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.3810493232859936, "learning_rate": 1.8897749455972673e-05, "loss": 0.3356, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.3637378782265528, "learning_rate": 1.884128556891707e-05, "loss": 0.3545, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.3905494279896328, "learning_rate": 1.878483094691119e-05, "loss": 0.3434, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.40275768405236445, "learning_rate": 1.8728386041364664e-05, "loss": 0.3232, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.40718351609830816, "learning_rate": 1.867195130360947e-05, "loss": 0.3405, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3937138401945244, "learning_rate": 1.8615527184896263e-05, "loss": 0.3583, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.3731348942531367, "learning_rate": 1.8559114136390795e-05, "loss": 0.3443, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.39515124843672744, "learning_rate": 1.8502712609170298e-05, "loss": 0.3361, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.3760423841037273, "learning_rate": 1.8446323054219876e-05, "loss": 0.3335, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.4160308766847197, "learning_rate": 1.838994592242891e-05, "loss": 0.3535, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.3713317489591168, "learning_rate": 1.8333581664587453e-05, "loss": 0.3189, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.39791613551806276, "learning_rate": 1.8277230731382593e-05, "loss": 0.3219, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.388260863600674, "learning_rate": 1.82208935733949e-05, "loss": 0.3211, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.39976707119708094, "learning_rate": 1.8164570641094793e-05, "loss": 0.3373, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3885236925368584, "learning_rate": 1.810826238483892e-05, "loss": 0.3513, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.39701799952995337, "learning_rate": 1.8051969254866608e-05, "loss": 0.335, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.3856362241933311, "learning_rate": 1.7995691701296226e-05, "loss": 0.3422, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.39150854939823676, "learning_rate": 1.7939430174121593e-05, "loss": 0.338, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.39014389607690725, "learning_rate": 1.788318512320838e-05, "loss": 0.3417, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.38237037987499395, "learning_rate": 1.782695699829051e-05, "loss": 0.3308, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.39269376595556954, "learning_rate": 1.7770746248966587e-05, "loss": 0.3263, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.36551447113953645, "learning_rate": 1.7714553324696243e-05, "loss": 0.3583, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3924878660725253, "learning_rate": 1.7658378674796614e-05, "loss": 0.3283, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3807033162727618, "learning_rate": 1.76022227484387e-05, "loss": 0.3336, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.37849315240738696, "learning_rate": 1.7546085994643807e-05, "loss": 0.3367, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.3827554531530246, "learning_rate": 1.7489968862279902e-05, "loss": 0.3282, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.4152058688352318, "learning_rate": 1.743387180005809e-05, "loss": 0.3165, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.38518776073689676, "learning_rate": 1.737779525652899e-05, "loss": 0.3396, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.40417672571254654, "learning_rate": 1.732173968007914e-05, "loss": 0.3442, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.3775425379793463, "learning_rate": 1.7265705518927437e-05, "loss": 0.3529, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.38009419358384594, "learning_rate": 1.7209693221121542e-05, "loss": 0.3333, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.43118606634066586, "learning_rate": 1.7153703234534302e-05, "loss": 0.3507, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.39375498526374103, "learning_rate": 1.709773600686015e-05, "loss": 0.3293, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.4022076913587939, "learning_rate": 1.7041791985611548e-05, "loss": 0.3538, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.4014161311687824, "learning_rate": 1.69858716181154e-05, "loss": 0.333, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.35515245033572346, "learning_rate": 1.692997535150948e-05, "loss": 0.3373, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.3618732168606987, "learning_rate": 1.687410363273884e-05, "loss": 0.3425, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.37290622123573236, "learning_rate": 1.6818256908552257e-05, "loss": 0.3316, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3783014346862132, "learning_rate": 1.6762435625498646e-05, "loss": 0.3403, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3742879618127826, "learning_rate": 1.67066402299235e-05, "loss": 0.3403, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.3759948293775134, "learning_rate": 1.6650871167965313e-05, "loss": 0.3528, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.3601581265527672, "learning_rate": 1.6595128885552028e-05, "loss": 0.3247, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.37768868015196355, "learning_rate": 1.653941382839745e-05, "loss": 0.3426, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.5646134925267209, "learning_rate": 1.6483726441997673e-05, "loss": 0.2407, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.36529629652430834, "learning_rate": 1.642806717162757e-05, "loss": 0.2557, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.4636584739553731, "learning_rate": 1.637243646233718e-05, "loss": 0.2122, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.6759948244431984, "learning_rate": 1.6316834758948174e-05, "loss": 0.2228, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.4490361405575234, "learning_rate": 1.6261262506050282e-05, "loss": 0.2074, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.45778427061204674, "learning_rate": 1.620572014799777e-05, "loss": 0.233, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.4910876308573399, "learning_rate": 1.6150208128905857e-05, "loss": 0.2342, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.4396680375644303, "learning_rate": 1.6094726892647147e-05, "loss": 0.2378, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.40221206760035566, "learning_rate": 1.6039276882848135e-05, "loss": 0.236, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.42785894114961653, "learning_rate": 1.5983858542885635e-05, "loss": 0.2331, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.4274751897251433, "learning_rate": 1.5928472315883203e-05, "loss": 0.2372, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.41577136672455384, "learning_rate": 1.5873118644707633e-05, "loss": 0.2254, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.4068692961686563, "learning_rate": 1.5817797971965413e-05, "loss": 0.2301, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.37707935369909495, "learning_rate": 1.576251073999917e-05, "loss": 0.2254, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.3917942112818776, "learning_rate": 1.5707257390884126e-05, "loss": 0.2261, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.37133146606613154, "learning_rate": 1.5652038366424595e-05, "loss": 0.2153, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3770238341386971, "learning_rate": 1.5596854108150424e-05, "loss": 0.227, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3833122956244234, "learning_rate": 1.5541705057313476e-05, "loss": 0.2378, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3732620889960936, "learning_rate": 1.5486591654884086e-05, "loss": 0.233, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.35950723374947297, "learning_rate": 1.543151434154755e-05, "loss": 0.2428, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.35746142043731416, "learning_rate": 1.5376473557700615e-05, "loss": 0.2316, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3571453873171147, "learning_rate": 1.5321469743447893e-05, "loss": 0.1937, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.36093383119922645, "learning_rate": 1.5266503338598434e-05, "loss": 0.2377, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3526790551651848, "learning_rate": 1.5211574782662149e-05, "loss": 0.2063, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.35516293977140895, "learning_rate": 1.5156684514846307e-05, "loss": 0.1977, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.34349968169965966, "learning_rate": 1.5101832974052012e-05, "loss": 0.2378, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3623305562395977, "learning_rate": 1.5047020598870737e-05, "loss": 0.219, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.35665785144260936, "learning_rate": 1.4992247827580778e-05, "loss": 0.203, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.3410307672050614, "learning_rate": 1.493751509814374e-05, "loss": 0.2309, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.32836886754324546, "learning_rate": 1.4882822848201073e-05, "loss": 0.2127, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.3430001639246268, "learning_rate": 1.4828171515070553e-05, "loss": 0.2339, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3567881298515565, "learning_rate": 1.4773561535742793e-05, "loss": 0.212, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.3356142434573614, "learning_rate": 1.4718993346877715e-05, "loss": 0.2283, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.3404602777356394, "learning_rate": 1.466446738480111e-05, "loss": 0.2367, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.32969924098612485, "learning_rate": 1.460998408550112e-05, "loss": 0.2333, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.34165459462918424, "learning_rate": 1.4555543884624751e-05, "loss": 0.224, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.324126027520061, "learning_rate": 1.4501147217474402e-05, "loss": 0.2212, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.32021635280703964, "learning_rate": 1.444679451900437e-05, "loss": 0.2356, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.33782890552681727, "learning_rate": 1.4392486223817397e-05, "loss": 0.2219, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3394066705220843, "learning_rate": 1.4338222766161143e-05, "loss": 0.2343, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.3278844767709395, "learning_rate": 1.4284004579924777e-05, "loss": 0.2235, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.3346874183660141, "learning_rate": 1.4229832098635479e-05, "loss": 0.2087, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.3434728303161705, "learning_rate": 1.4175705755454963e-05, "loss": 0.2094, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.3447101112880997, "learning_rate": 1.412162598317602e-05, "loss": 0.2146, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.32368887811927927, "learning_rate": 1.406759321421907e-05, "loss": 0.2284, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3385826709113282, "learning_rate": 1.401360788062871e-05, "loss": 0.2289, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.3359652700222867, "learning_rate": 1.3959670414070204e-05, "loss": 0.211, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.3196147499171942, "learning_rate": 1.3905781245826108e-05, "loss": 0.2565, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.3304895322812084, "learning_rate": 1.3851940806792778e-05, "loss": 0.2216, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3336643862595795, "learning_rate": 1.379814952747693e-05, "loss": 0.2238, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.32908453167471113, "learning_rate": 1.3744407837992193e-05, "loss": 0.2178, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.33620564994887336, "learning_rate": 1.3690716168055692e-05, "loss": 0.2225, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.3577317742049263, "learning_rate": 1.363707494698459e-05, "loss": 0.2275, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.32935976102001263, "learning_rate": 1.358348460369265e-05, "loss": 0.2286, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.32209495701125673, "learning_rate": 1.352994556668684e-05, "loss": 0.2216, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3496876337586769, "learning_rate": 1.3476458264063865e-05, "loss": 0.2374, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.3366572031227864, "learning_rate": 1.342302312350678e-05, "loss": 0.235, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3216752200618341, "learning_rate": 1.3369640572281537e-05, "loss": 0.2224, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.314379329075051, "learning_rate": 1.3316311037233596e-05, "loss": 0.2223, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.3289674844999062, "learning_rate": 1.326303494478451e-05, "loss": 0.2084, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3315645314746781, "learning_rate": 1.3209812720928472e-05, "loss": 0.2147, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.32458575790994226, "learning_rate": 1.315664479122898e-05, "loss": 0.2197, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.32965676653738624, "learning_rate": 1.3103531580815378e-05, "loss": 0.2273, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.3255067793648135, "learning_rate": 1.3050473514379488e-05, "loss": 0.2288, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.31915025022831284, "learning_rate": 1.2997471016172188e-05, "loss": 0.233, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.32069349545201603, "learning_rate": 1.2944524510000042e-05, "loss": 0.2258, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.3313326439790728, "learning_rate": 1.2891634419221908e-05, "loss": 0.2305, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.31792216906345006, "learning_rate": 1.2838801166745545e-05, "loss": 0.2183, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.312505851891398, "learning_rate": 1.2786025175024216e-05, "loss": 0.2249, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.32464716746823885, "learning_rate": 1.2733306866053357e-05, "loss": 0.2414, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.3415274531228935, "learning_rate": 1.2680646661367163e-05, "loss": 0.2175, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.3229490958169421, "learning_rate": 1.2628044982035219e-05, "loss": 0.219, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.34250287845839544, "learning_rate": 1.2575502248659155e-05, "loss": 0.2324, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.3430119870392195, "learning_rate": 1.2523018881369269e-05, "loss": 0.2054, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.33374749279387705, "learning_rate": 1.2470595299821176e-05, "loss": 0.236, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.3241292480657709, "learning_rate": 1.2418231923192416e-05, "loss": 0.2051, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.3315456762509865, "learning_rate": 1.2365929170179165e-05, "loss": 0.2277, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.3342526380197505, "learning_rate": 1.2313687458992848e-05, "loss": 0.2154, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.33533733994858494, "learning_rate": 1.2261507207356785e-05, "loss": 0.2209, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.33157155595919574, "learning_rate": 1.220938883250288e-05, "loss": 0.225, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.3386831212069322, "learning_rate": 1.215733275116827e-05, "loss": 0.2213, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.3232481627952182, "learning_rate": 1.2105339379592005e-05, "loss": 0.2341, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.3418864548857361, "learning_rate": 1.2053409133511681e-05, "loss": 0.2359, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.32975711725337326, "learning_rate": 1.2001542428160173e-05, "loss": 0.2258, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.31697566524688253, "learning_rate": 1.1949739678262278e-05, "loss": 0.2284, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.31805819635998817, "learning_rate": 1.189800129803139e-05, "loss": 0.2149, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3242672180825721, "learning_rate": 1.1846327701166228e-05, "loss": 0.2301, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.3359810182654098, "learning_rate": 1.1794719300847493e-05, "loss": 0.2099, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.3292077054188685, "learning_rate": 1.1743176509734582e-05, "loss": 0.2149, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.3370836724225387, "learning_rate": 1.1691699739962275e-05, "loss": 0.2266, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.32175942890873305, "learning_rate": 1.1640289403137456e-05, "loss": 0.251, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.3445482445574779, "learning_rate": 1.1588945910335802e-05, "loss": 0.2361, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.34303652868862095, "learning_rate": 1.1537669672098517e-05, "loss": 0.2136, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.31301705488540466, "learning_rate": 1.1486461098429036e-05, "loss": 0.2376, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.31492168700094647, "learning_rate": 1.1435320598789747e-05, "loss": 0.2356, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.33284609046499586, "learning_rate": 1.1384248582098736e-05, "loss": 0.2234, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.3271373460541087, "learning_rate": 1.1333245456726467e-05, "loss": 0.2133, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.3381512347717084, "learning_rate": 1.128231163049258e-05, "loss": 0.1987, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.3345158347167013, "learning_rate": 1.123144751066259e-05, "loss": 0.2202, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.3345628186987631, "learning_rate": 1.1180653503944657e-05, "loss": 0.2177, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.332126832040439, "learning_rate": 1.1129930016486287e-05, "loss": 0.2113, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.3411521800526333, "learning_rate": 1.107927745387114e-05, "loss": 0.2211, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.3288215905842972, "learning_rate": 1.1028696221115766e-05, "loss": 0.2448, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.31835240686159405, "learning_rate": 1.0978186722666341e-05, "loss": 0.2389, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.3133095353270695, "learning_rate": 1.0927749362395475e-05, "loss": 0.2102, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.3280543189466125, "learning_rate": 1.0877384543598954e-05, "loss": 0.2256, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.31736965684245483, "learning_rate": 1.0827092668992529e-05, "loss": 0.2289, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.34107354661847994, "learning_rate": 1.077687414070869e-05, "loss": 0.2342, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.32964552100257216, "learning_rate": 1.0726729360293451e-05, "loss": 0.2062, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.3294232799730653, "learning_rate": 1.0676658728703147e-05, "loss": 0.2413, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.32315058155239623, "learning_rate": 1.0626662646301198e-05, "loss": 0.2188, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.324680925627202, "learning_rate": 1.0576741512854958e-05, "loss": 0.2356, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.3147169166124755, "learning_rate": 1.052689572753247e-05, "loss": 0.2163, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.3185323931210019, "learning_rate": 1.0477125688899328e-05, "loss": 0.2294, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.3248116210877451, "learning_rate": 1.0427431794915406e-05, "loss": 0.2169, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.32977001521492194, "learning_rate": 1.0377814442931769e-05, "loss": 0.2051, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.3218755147295996, "learning_rate": 1.0328274029687439e-05, "loss": 0.2133, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.33745396347900586, "learning_rate": 1.0278810951306253e-05, "loss": 0.2185, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.33180738605839805, "learning_rate": 1.0229425603293647e-05, "loss": 0.2148, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.3160591190751334, "learning_rate": 1.0180118380533558e-05, "loss": 0.1955, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.33235261648521197, "learning_rate": 1.0130889677285225e-05, "loss": 0.2288, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.33240942392658834, "learning_rate": 1.008173988718005e-05, "loss": 0.2254, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.3185636705134369, "learning_rate": 1.0032669403218439e-05, "loss": 0.2185, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.3172844226329805, "learning_rate": 9.983678617766677e-06, "loss": 0.2354, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.3232975593009229, "learning_rate": 9.934767922553788e-06, "loss": 0.2244, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.3391221261817803, "learning_rate": 9.885937708668371e-06, "loss": 0.212, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.32749576531718616, "learning_rate": 9.837188366555524e-06, "loss": 0.2398, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.3106477379254822, "learning_rate": 9.788520286013691e-06, "loss": 0.2263, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.32331139587021823, "learning_rate": 9.739933856191537e-06, "loss": 0.2208, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.31975561279319376, "learning_rate": 9.691429465584866e-06, "loss": 0.215, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.3135762624466074, "learning_rate": 9.643007502033492e-06, "loss": 0.2339, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.3240643397374953, "learning_rate": 9.594668352718152e-06, "loss": 0.2211, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.3295004481411132, "learning_rate": 9.546412404157383e-06, "loss": 0.2143, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.3159572652283642, "learning_rate": 9.498240042204471e-06, "loss": 0.203, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.32496331198219625, "learning_rate": 9.450151652044339e-06, "loss": 0.2263, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.3382872896436829, "learning_rate": 9.402147618190472e-06, "loss": 0.2135, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.3443944947172035, "learning_rate": 9.354228324481841e-06, "loss": 0.2281, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.32470933663373547, "learning_rate": 9.306394154079852e-06, "loss": 0.2289, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.3259117693282018, "learning_rate": 9.258645489465254e-06, "loss": 0.2255, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.3132793339071538, "learning_rate": 9.21098271243509e-06, "loss": 0.2447, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.31627647948510446, "learning_rate": 9.163406204099659e-06, "loss": 0.2227, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.33726877062806104, "learning_rate": 9.115916344879452e-06, "loss": 0.2088, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.3237277070676502, "learning_rate": 9.068513514502126e-06, "loss": 0.2246, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.31479808835421574, "learning_rate": 9.021198091999439e-06, "loss": 0.2197, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.3131719686823155, "learning_rate": 8.973970455704251e-06, "loss": 0.2246, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.32900517213856273, "learning_rate": 8.926830983247495e-06, "loss": 0.2235, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.31705012357933116, "learning_rate": 8.879780051555116e-06, "loss": 0.219, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.3120753408019726, "learning_rate": 8.83281803684512e-06, "loss": 0.2201, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.33220638710041744, "learning_rate": 8.785945314624532e-06, "loss": 0.2239, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.3131420462725812, "learning_rate": 8.739162259686385e-06, "loss": 0.2368, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.3117066145777668, "learning_rate": 8.692469246106734e-06, "loss": 0.2226, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.3282006775461376, "learning_rate": 8.645866647241677e-06, "loss": 0.2158, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.31878868990782416, "learning_rate": 8.599354835724348e-06, "loss": 0.2304, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.3257768920710309, "learning_rate": 8.552934183461958e-06, "loss": 0.2231, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.31437857481639914, "learning_rate": 8.506605061632805e-06, "loss": 0.214, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.3078289433576719, "learning_rate": 8.460367840683308e-06, "loss": 0.2202, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.32242641078021045, "learning_rate": 8.414222890325065e-06, "loss": 0.2266, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.3284555738797834, "learning_rate": 8.368170579531855e-06, "loss": 0.2413, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.31695256956928874, "learning_rate": 8.322211276536733e-06, "loss": 0.2251, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.3037886196488758, "learning_rate": 8.27634534882907e-06, "loss": 0.2435, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.3180551013517624, "learning_rate": 8.230573163151585e-06, "loss": 0.2357, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.31947681727220345, "learning_rate": 8.184895085497466e-06, "loss": 0.2183, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.3195945079586037, "learning_rate": 8.139311481107401e-06, "loss": 0.2071, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.3326416352368083, "learning_rate": 8.093822714466686e-06, "loss": 0.2106, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.30469737172588746, "learning_rate": 8.048429149302271e-06, "loss": 0.2308, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.30935149186783384, "learning_rate": 8.003131148579902e-06, "loss": 0.2292, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.32229542655625015, "learning_rate": 7.957929074501182e-06, "loss": 0.2249, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.3168464175096869, "learning_rate": 7.912823288500695e-06, "loss": 0.2089, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.3234470794880372, "learning_rate": 7.867814151243102e-06, "loss": 0.2154, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.31912893650860125, "learning_rate": 7.822902022620267e-06, "loss": 0.2287, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.33196322711962134, "learning_rate": 7.778087261748377e-06, "loss": 0.2047, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.3148747172359465, "learning_rate": 7.733370226965056e-06, "loss": 0.2382, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.3208252628877219, "learning_rate": 7.688751275826527e-06, "loss": 0.2134, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.34240462481103984, "learning_rate": 7.644230765104735e-06, "loss": 0.227, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.31943059615770203, "learning_rate": 7.599809050784502e-06, "loss": 0.2171, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.31904495665853244, "learning_rate": 7.555486488060661e-06, "loss": 0.2195, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.3204510189159362, "learning_rate": 7.511263431335249e-06, "loss": 0.2207, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.3092453243755458, "learning_rate": 7.467140234214656e-06, "loss": 0.2389, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.301949580333843, "learning_rate": 7.423117249506777e-06, "loss": 0.2231, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.3165591546684567, "learning_rate": 7.379194829218231e-06, "loss": 0.2163, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.3034327759930836, "learning_rate": 7.335373324551518e-06, "loss": 0.2247, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.32887629190918943, "learning_rate": 7.291653085902224e-06, "loss": 0.217, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.33007051321099273, "learning_rate": 7.248034462856213e-06, "loss": 0.2217, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.32206734094310285, "learning_rate": 7.20451780418683e-06, "loss": 0.2137, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.3120278947062535, "learning_rate": 7.161103457852128e-06, "loss": 0.2273, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.31400431209181173, "learning_rate": 7.117791770992046e-06, "loss": 0.2069, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.3175068935643887, "learning_rate": 7.074583089925688e-06, "loss": 0.2319, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.3092409826495777, "learning_rate": 7.0314777601485155e-06, "loss": 0.2263, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.32052236112710225, "learning_rate": 6.988476126329604e-06, "loss": 0.2433, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.3144370161992377, "learning_rate": 6.945578532308857e-06, "loss": 0.2381, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.3047344946836447, "learning_rate": 6.902785321094301e-06, "loss": 0.2373, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.3206530752781988, "learning_rate": 6.8600968348593115e-06, "loss": 0.2342, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.31232214326939445, "learning_rate": 6.817513414939892e-06, "loss": 0.2232, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.32710900341888355, "learning_rate": 6.775035401831924e-06, "loss": 0.2009, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.3127028661735833, "learning_rate": 6.732663135188473e-06, "loss": 0.2284, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.31564071748213907, "learning_rate": 6.690396953817055e-06, "loss": 0.2432, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.3060646564624553, "learning_rate": 6.648237195676927e-06, "loss": 0.2131, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.30311153833359405, "learning_rate": 6.606184197876395e-06, "loss": 0.2382, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.30624144297881833, "learning_rate": 6.564238296670109e-06, "loss": 0.2377, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.3219707111395721, "learning_rate": 6.52239982745638e-06, "loss": 0.2111, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.3160825658085068, "learning_rate": 6.480669124774484e-06, "loss": 0.2097, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.33062793803386403, "learning_rate": 6.439046522302013e-06, "loss": 0.2349, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.31569577935146526, "learning_rate": 6.397532352852191e-06, "loss": 0.2207, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.3062340349753657, "learning_rate": 6.356126948371202e-06, "loss": 0.2137, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.3258106087004682, "learning_rate": 6.314830639935559e-06, "loss": 0.2219, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.30378114442352466, "learning_rate": 6.273643757749448e-06, "loss": 0.2435, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.3091143996658343, "learning_rate": 6.2325666311420856e-06, "loss": 0.2134, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.31640745708656093, "learning_rate": 6.1915995885650675e-06, "loss": 0.1959, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.33791512044108113, "learning_rate": 6.150742957589784e-06, "loss": 0.2114, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.3178106625547147, "learning_rate": 6.109997064904774e-06, "loss": 0.2232, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.31137994943652175, "learning_rate": 6.069362236313092e-06, "loss": 0.2183, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.3071706338955741, "learning_rate": 6.0288387967297565e-06, "loss": 0.2419, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.33264479017211374, "learning_rate": 5.988427070179108e-06, "loss": 0.2328, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.3216630741964466, "learning_rate": 5.948127379792234e-06, "loss": 0.204, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.32052919488114684, "learning_rate": 5.90794004780439e-06, "loss": 0.2027, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.3223770629954033, "learning_rate": 5.867865395552405e-06, "loss": 0.2295, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.3150057023371792, "learning_rate": 5.8279037434721364e-06, "loss": 0.2175, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.3128739255880599, "learning_rate": 5.788055411095892e-06, "loss": 0.2189, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.305980409602628, "learning_rate": 5.7483207170498625e-06, "loss": 0.2142, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.3149912586767217, "learning_rate": 5.708699979051613e-06, "loss": 0.194, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.32059884032457453, "learning_rate": 5.66919351390751e-06, "loss": 0.2293, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.3204583972771047, "learning_rate": 5.629801637510188e-06, "loss": 0.2182, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.3267181355473172, "learning_rate": 5.590524664836043e-06, "loss": 0.2212, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.30816045848926, "learning_rate": 5.551362909942708e-06, "loss": 0.2188, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.30207029772236377, "learning_rate": 5.51231668596653e-06, "loss": 0.2249, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.3104625668485866, "learning_rate": 5.47338630512007e-06, "loss": 0.2092, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.3147568030877948, "learning_rate": 5.434572078689617e-06, "loss": 0.2253, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.2969099565563886, "learning_rate": 5.395874317032694e-06, "loss": 0.2096, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.31103147298213923, "learning_rate": 5.357293329575573e-06, "loss": 0.2129, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.31263305688729, "learning_rate": 5.318829424810797e-06, "loss": 0.199, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.3120975912336322, "learning_rate": 5.280482910294728e-06, "loss": 0.2332, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.3152926637666945, "learning_rate": 5.242254092645078e-06, "loss": 0.225, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.3087404724825189, "learning_rate": 5.2041432775384445e-06, "loss": 0.2049, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.3035099512806307, "learning_rate": 5.166150769707892e-06, "loss": 0.2202, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.31948000380785524, "learning_rate": 5.128276872940503e-06, "loss": 0.2119, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.3088015914439519, "learning_rate": 5.090521890074953e-06, "loss": 0.231, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.30141385525132847, "learning_rate": 5.0528861229990675e-06, "loss": 0.2149, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.3083365152139102, "learning_rate": 5.015369872647442e-06, "loss": 0.2097, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2938371943072384, "learning_rate": 4.9779734389990195e-06, "loss": 0.212, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.30520146948233845, "learning_rate": 4.940697121074675e-06, "loss": 0.2225, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.31755860819421217, "learning_rate": 4.903541216934864e-06, "loss": 0.2245, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.31381212961723715, "learning_rate": 4.8665060236772e-06, "loss": 0.2232, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.31280177556220895, "learning_rate": 4.829591837434102e-06, "loss": 0.2114, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.31982422667157, "learning_rate": 4.792798953370424e-06, "loss": 0.2291, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.3078452308424996, "learning_rate": 4.756127665681083e-06, "loss": 0.2429, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.3159171319358215, "learning_rate": 4.719578267588725e-06, "loss": 0.2259, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.3117729055891642, "learning_rate": 4.6831510513413525e-06, "loss": 0.2152, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4812352405866327, "learning_rate": 4.6468463082100176e-06, "loss": 0.1878, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.3991458884886887, "learning_rate": 4.610664328486485e-06, "loss": 0.1503, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.3257949249064859, "learning_rate": 4.5746054014809e-06, "loss": 0.1681, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.2697666336694185, "learning_rate": 4.5386698155194766e-06, "loss": 0.1554, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.30632927949721256, "learning_rate": 4.502857857942204e-06, "loss": 0.1478, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.4328569251992743, "learning_rate": 4.467169815100549e-06, "loss": 0.1541, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.49873507888285284, "learning_rate": 4.431605972355137e-06, "loss": 0.1551, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.4175090482313436, "learning_rate": 4.396166614073516e-06, "loss": 0.1718, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.3180309149584463, "learning_rate": 4.360852023627846e-06, "loss": 0.1639, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.36439864362621444, "learning_rate": 4.325662483392656e-06, "loss": 0.1665, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.3716608630845479, "learning_rate": 4.29059827474257e-06, "loss": 0.1806, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.3624851847236307, "learning_rate": 4.255659678050063e-06, "loss": 0.1695, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.3110785828228747, "learning_rate": 4.22084697268323e-06, "loss": 0.1569, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.28791008819696673, "learning_rate": 4.186160437003535e-06, "loss": 0.1842, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.3002550047621571, "learning_rate": 4.151600348363582e-06, "loss": 0.1793, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.3226632767367694, "learning_rate": 4.11716698310493e-06, "loss": 0.173, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.30702756036901213, "learning_rate": 4.082860616555848e-06, "loss": 0.1615, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.276919723429804, "learning_rate": 4.048681523029125e-06, "loss": 0.1492, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2911529145184361, "learning_rate": 4.014629975819882e-06, "loss": 0.1459, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.2807951092679747, "learning_rate": 3.9807062472033855e-06, "loss": 0.159, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2885790034845906, "learning_rate": 3.94691060843287e-06, "loss": 0.168, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.2648957164540711, "learning_rate": 3.913243329737353e-06, "loss": 0.1621, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.3009326475742596, "learning_rate": 3.879704680319503e-06, "loss": 0.1532, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.28607933004707514, "learning_rate": 3.846294928353471e-06, "loss": 0.142, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.2704469879413577, "learning_rate": 3.8130143409827345e-06, "loss": 0.1478, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.28687570842126764, "learning_rate": 3.7798631843179887e-06, "loss": 0.1655, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2755427118874498, "learning_rate": 3.7468417234349973e-06, "loss": 0.152, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2579059744137273, "learning_rate": 3.7139502223724823e-06, "loss": 0.1705, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2539600739478793, "learning_rate": 3.6811889441300095e-06, "loss": 0.152, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.27342308298174395, "learning_rate": 3.648558150665886e-06, "loss": 0.145, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.2506132594878167, "learning_rate": 3.616058102895075e-06, "loss": 0.15, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.26940373225333686, "learning_rate": 3.583689060687079e-06, "loss": 0.166, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.2729067897383749, "learning_rate": 3.5514512828639023e-06, "loss": 0.1649, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.2676672213059132, "learning_rate": 3.51934502719796e-06, "loss": 0.1471, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.2622628397863503, "learning_rate": 3.4873705504100185e-06, "loss": 0.1649, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.25607566332576703, "learning_rate": 3.4555281081671345e-06, "loss": 0.1446, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.26606630325831027, "learning_rate": 3.4238179550806326e-06, "loss": 0.1683, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.26608784549029835, "learning_rate": 3.3922403447040497e-06, "loss": 0.1813, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.26383127813202306, "learning_rate": 3.3607955295311247e-06, "loss": 0.1534, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.26533961252400123, "learning_rate": 3.32948376099375e-06, "loss": 0.155, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.25842964473212165, "learning_rate": 3.2983052894599976e-06, "loss": 0.1496, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2658970697511017, "learning_rate": 3.2672603642320945e-06, "loss": 0.1634, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2617650312243642, "learning_rate": 3.236349233544438e-06, "loss": 0.1684, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2519136874665494, "learning_rate": 3.205572144561604e-06, "loss": 0.1691, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2533428818805943, "learning_rate": 3.174929343376374e-06, "loss": 0.1592, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2600135310674634, "learning_rate": 3.1444210750077777e-06, "loss": 0.1647, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2675954918747688, "learning_rate": 3.1140475833991046e-06, "loss": 0.1397, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.25740896140788694, "learning_rate": 3.0838091114159895e-06, "loss": 0.1607, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2424479258398624, "learning_rate": 3.0537059008444524e-06, "loss": 0.1569, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.27036967313623755, "learning_rate": 3.0237381923889563e-06, "loss": 0.181, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.2597517041940827, "learning_rate": 2.9939062256704997e-06, "loss": 0.1582, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.25797845441426426, "learning_rate": 2.964210239224696e-06, "loss": 0.1643, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.2529765610271376, "learning_rate": 2.934650470499869e-06, "loss": 0.1681, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.26440466406235913, "learning_rate": 2.905227155855128e-06, "loss": 0.1519, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2616248154369242, "learning_rate": 2.875940530558519e-06, "loss": 0.1535, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.26844838918532843, "learning_rate": 2.8467908287851154e-06, "loss": 0.1618, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.25492930058469815, "learning_rate": 2.8177782836151603e-06, "loss": 0.1826, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.25853774480383157, "learning_rate": 2.7889031270321874e-06, "loss": 0.1661, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2583184630760193, "learning_rate": 2.760165589921184e-06, "loss": 0.1685, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.25474936365931494, "learning_rate": 2.7315659020667305e-06, "loss": 0.1742, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2494137998342939, "learning_rate": 2.703104292151164e-06, "loss": 0.1543, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.2583331419090311, "learning_rate": 2.6747809877527607e-06, "loss": 0.1431, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.27413933625106757, "learning_rate": 2.6465962153439082e-06, "loss": 0.1587, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.2522502059396916, "learning_rate": 2.618550200289303e-06, "loss": 0.1377, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2609226624175513, "learning_rate": 2.59064316684412e-06, "loss": 0.1702, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.2472567479939364, "learning_rate": 2.562875338152264e-06, "loss": 0.1625, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.25866498825855105, "learning_rate": 2.5352469362445552e-06, "loss": 0.1599, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.25407859532269006, "learning_rate": 2.5077581820369523e-06, "loss": 0.1392, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.2542278274695762, "learning_rate": 2.480409295328803e-06, "loss": 0.1519, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.253150388724193, "learning_rate": 2.45320049480108e-06, "loss": 0.1556, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.2615751496220713, "learning_rate": 2.4261319980146293e-06, "loss": 0.1921, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.266574379545441, "learning_rate": 2.399204021408421e-06, "loss": 0.168, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.25817869090066886, "learning_rate": 2.3724167802978395e-06, "loss": 0.1561, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.26182704716011324, "learning_rate": 2.3457704888729625e-06, "loss": 0.1537, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.26223458197363636, "learning_rate": 2.3192653601968162e-06, "loss": 0.1515, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.2506454670701916, "learning_rate": 2.2929016062037057e-06, "loss": 0.1685, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.25810284941358974, "learning_rate": 2.2666794376975055e-06, "loss": 0.1515, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2641745932742011, "learning_rate": 2.24059906434998e-06, "loss": 0.1709, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.253918855417797, "learning_rate": 2.214660694699091e-06, "loss": 0.1577, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.24454063921505984, "learning_rate": 2.188864536147355e-06, "loss": 0.1506, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2622494018809739, "learning_rate": 2.1632107949601757e-06, "loss": 0.1806, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2647886598776036, "learning_rate": 2.137699676264171e-06, "loss": 0.1723, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.2581205188849891, "learning_rate": 2.1123313840455738e-06, "loss": 0.1643, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.25497117040726464, "learning_rate": 2.08710612114857e-06, "loss": 0.1692, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2633417287776785, "learning_rate": 2.0620240892736953e-06, "loss": 0.1652, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.26465455209901534, "learning_rate": 2.0370854889762e-06, "loss": 0.1472, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.25316695805731915, "learning_rate": 2.0122905196644726e-06, "loss": 0.1379, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.2524230132136117, "learning_rate": 1.987639379598427e-06, "loss": 0.1368, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.25683939638494707, "learning_rate": 1.963132265887919e-06, "loss": 0.1831, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.2677067915388052, "learning_rate": 1.9387693744911784e-06, "loss": 0.1702, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.27353392757699596, "learning_rate": 1.9145509002132368e-06, "loss": 0.1595, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.25785022979642963, "learning_rate": 1.8904770367043723e-06, "loss": 0.1585, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.24832411699411105, "learning_rate": 1.8665479764585504e-06, "loss": 0.1743, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.25962622613545877, "learning_rate": 1.8427639108118977e-06, "loss": 0.1795, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.25233407006661573, "learning_rate": 1.8191250299411755e-06, "loss": 0.1679, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2540574712636902, "learning_rate": 1.7956315228622446e-06, "loss": 0.1666, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2632219610183352, "learning_rate": 1.7722835774285553e-06, "loss": 0.1267, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.25228512471099895, "learning_rate": 1.7490813803296624e-06, "loss": 0.1811, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2587559870719135, "learning_rate": 1.726025117089718e-06, "loss": 0.1564, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2554789379810635, "learning_rate": 1.70311497206598e-06, "loss": 0.1504, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.25585809759526523, "learning_rate": 1.6803511284473638e-06, "loss": 0.1578, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.25676524216692614, "learning_rate": 1.6577337682529538e-06, "loss": 0.1593, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2505069731231986, "learning_rate": 1.6352630723305617e-06, "loss": 0.1766, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2626091349101648, "learning_rate": 1.612939220355272e-06, "loss": 0.1565, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.2502122095830301, "learning_rate": 1.5907623908280112e-06, "loss": 0.1829, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.25179164583669855, "learning_rate": 1.568732761074121e-06, "loss": 0.1531, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.2568197173090144, "learning_rate": 1.5468505072419237e-06, "loss": 0.1483, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.2502898247952105, "learning_rate": 1.5251158043013448e-06, "loss": 0.1541, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.27873767114341014, "learning_rate": 1.5035288260424885e-06, "loss": 0.1605, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.2588224700131823, "learning_rate": 1.4820897450742623e-06, "loss": 0.1492, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.24832081986511748, "learning_rate": 1.4607987328229767e-06, "loss": 0.1598, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.3121789626574811, "learning_rate": 1.4396559595310056e-06, "loss": 0.1524, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2482405355732299, "learning_rate": 1.4186615942553973e-06, "loss": 0.1485, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2463672822243743, "learning_rate": 1.3978158048665424e-06, "loss": 0.1805, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2550992484308585, "learning_rate": 1.3771187580468115e-06, "loss": 0.1774, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.23808531807205538, "learning_rate": 1.3565706192892392e-06, "loss": 0.1582, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.25040502264587566, "learning_rate": 1.3361715528961993e-06, "loss": 0.1673, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.26545486216721276, "learning_rate": 1.3159217219780817e-06, "loss": 0.143, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.24927325539510425, "learning_rate": 1.2958212884519949e-06, "loss": 0.1756, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.25081698694423943, "learning_rate": 1.2758704130404675e-06, "loss": 0.157, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.24878981297439398, "learning_rate": 1.2560692552701738e-06, "loss": 0.157, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.25890370009019764, "learning_rate": 1.2364179734706382e-06, "loss": 0.1597, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.25207068172596, "learning_rate": 1.2169167247729852e-06, "loss": 0.1747, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2478949088364925, "learning_rate": 1.1975656651086864e-06, "loss": 0.1686, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.259426160927151, "learning_rate": 1.1783649492082926e-06, "loss": 0.162, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.25568817519429465, "learning_rate": 1.1593147306002183e-06, "loss": 0.1429, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2654114175324629, "learning_rate": 1.140415161609505e-06, "loss": 0.188, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2557459808044359, "learning_rate": 1.121666393356604e-06, "loss": 0.1769, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2520695847407853, "learning_rate": 1.1030685757561632e-06, "loss": 0.1501, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.25352998793102144, "learning_rate": 1.0846218575158373e-06, "loss": 0.1723, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.2640019609635044, "learning_rate": 1.066326386135097e-06, "loss": 0.1707, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.24545704083511477, "learning_rate": 1.0481823079040398e-06, "loss": 0.1548, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.252617806763539, "learning_rate": 1.0301897679022344e-06, "loss": 0.1708, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.2520961769423602, "learning_rate": 1.0123489099975491e-06, "loss": 0.1648, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.24618338198098674, "learning_rate": 9.9465987684501e-07, "loss": 0.1476, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.24999593180791962, "learning_rate": 9.771228098856534e-07, "loss": 0.1457, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.25356940911775255, "learning_rate": 9.597378493454013e-07, "loss": 0.1679, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.25431329345730386, "learning_rate": 9.425051342339353e-07, "loss": 0.1645, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.24906898344408746, "learning_rate": 9.254248023435864e-07, "loss": 0.1625, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.2482342430597535, "learning_rate": 9.084969902482288e-07, "loss": 0.137, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.2702708851618281, "learning_rate": 8.917218333021993e-07, "loss": 0.1615, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2534244778114693, "learning_rate": 8.750994656392109e-07, "loss": 0.1623, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.25222897960886076, "learning_rate": 8.58630020171265e-07, "loss": 0.165, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2656973884656898, "learning_rate": 8.423136285876099e-07, "loss": 0.1564, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.25892388975244635, "learning_rate": 8.26150421353682e-07, "loss": 0.1482, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2508890449627227, "learning_rate": 8.101405277100549e-07, "loss": 0.1566, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2609559396225389, "learning_rate": 7.942840756714077e-07, "loss": 0.146, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.2462371401916699, "learning_rate": 7.785811920255093e-07, "loss": 0.1659, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.25792969711607744, "learning_rate": 7.630320023322024e-07, "loss": 0.1542, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.2485862628578413, "learning_rate": 7.476366309223903e-07, "loss": 0.1388, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.25483093371327925, "learning_rate": 7.323952008970537e-07, "loss": 0.1881, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.25151002265505074, "learning_rate": 7.173078341262618e-07, "loss": 0.1616, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2583506727241696, "learning_rate": 7.023746512481989e-07, "loss": 0.1572, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.25498602646292345, "learning_rate": 6.875957716681902e-07, "loss": 0.1321, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.25194286872255695, "learning_rate": 6.729713135577687e-07, "loss": 0.1776, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.26486837672325375, "learning_rate": 6.585013938537143e-07, "loss": 0.1548, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2507073498031774, "learning_rate": 6.441861282571115e-07, "loss": 0.1531, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.23975062448591153, "learning_rate": 6.300256312324471e-07, "loss": 0.1552, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2525316902748685, "learning_rate": 6.160200160066776e-07, "loss": 0.1478, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.26279170457969236, "learning_rate": 6.021693945683327e-07, "loss": 0.1702, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.2585054198586498, "learning_rate": 5.884738776666044e-07, "loss": 0.1684, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.241606006010772, "learning_rate": 5.749335748104878e-07, "loss": 0.1511, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.26012610277796877, "learning_rate": 5.615485942678778e-07, "loss": 0.1516, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.24064340876384657, "learning_rate": 5.483190430647289e-07, "loss": 0.1504, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.2505397971694104, "learning_rate": 5.352450269841747e-07, "loss": 0.1701, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.2590440880792669, "learning_rate": 5.22326650565701e-07, "loss": 0.1619, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2633254782661007, "learning_rate": 5.095640171043048e-07, "loss": 0.1488, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.24295644363498492, "learning_rate": 4.969572286496594e-07, "loss": 0.1988, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.26504210604072803, "learning_rate": 4.845063860053079e-07, "loss": 0.1699, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.24802709097429212, "learning_rate": 4.7221158872785997e-07, "loss": 0.1609, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.2513420081837456, "learning_rate": 4.600729351261857e-07, "loss": 0.1627, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.25649327205013234, "learning_rate": 4.4809052226063355e-07, "loss": 0.1683, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.25875249294933256, "learning_rate": 4.3626444594226046e-07, "loss": 0.1598, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2502157950566502, "learning_rate": 4.245948007320588e-07, "loss": 0.1539, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.24873537515113892, "learning_rate": 4.130816799401971e-07, "loss": 0.1591, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.2483099605035417, "learning_rate": 4.017251756252827e-07, "loss": 0.1683, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.24972231843957712, "learning_rate": 3.9052537859362473e-07, "loss": 0.1585, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2614769851138557, "learning_rate": 3.7948237839849687e-07, "loss": 0.1524, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.2532613090940285, "learning_rate": 3.6859626333943797e-07, "loss": 0.164, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.24495530700123844, "learning_rate": 3.578671204615347e-07, "loss": 0.1762, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.25562775148321587, "learning_rate": 3.472950355547267e-07, "loss": 0.1504, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.24395364708569053, "learning_rate": 3.3688009315312244e-07, "loss": 0.1635, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2557458946915014, "learning_rate": 3.266223765343224e-07, "loss": 0.1787, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.26346143969799835, "learning_rate": 3.16521967718757e-07, "loss": 0.1786, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.2507727487606864, "learning_rate": 3.0657894746902726e-07, "loss": 0.1582, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.2538025138757573, "learning_rate": 2.9679339528925654e-07, "loss": 0.1734, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.23971992539143597, "learning_rate": 2.871653894244597e-07, "loss": 0.1633, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.24219586551501432, "learning_rate": 2.7769500685991266e-07, "loss": 0.1713, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.26134907022330117, "learning_rate": 2.683823233205485e-07, "loss": 0.1673, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.26183929944248346, "learning_rate": 2.592274132703287e-07, "loss": 0.1483, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.25316266116963415, "learning_rate": 2.502303499116754e-07, "loss": 0.145, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.24968848322835424, "learning_rate": 2.413912051848666e-07, "loss": 0.1396, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.24375882558220804, "learning_rate": 2.3271004976746613e-07, "loss": 0.1575, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.25763933618061124, "learning_rate": 2.2418695307376393e-07, "loss": 0.1547, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.25111924826117027, "learning_rate": 2.1582198325420968e-07, "loss": 0.1783, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.25493779001161987, "learning_rate": 2.0761520719488447e-07, "loss": 0.1598, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.24814647437585546, "learning_rate": 1.9956669051694798e-07, "loss": 0.1624, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.25016074435615393, "learning_rate": 1.916764975761254e-07, "loss": 0.1706, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.24845807863760527, "learning_rate": 1.839446914621923e-07, "loss": 0.1951, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.26313385643127035, "learning_rate": 1.7637133399845962e-07, "loss": 0.1686, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.24358416125372542, "learning_rate": 1.6895648574129397e-07, "loss": 0.1734, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.26608421870850124, "learning_rate": 1.6170020597962465e-07, "loss": 0.1609, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.24517712806234235, "learning_rate": 1.5460255273447078e-07, "loss": 0.1734, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.25803691122357564, "learning_rate": 1.4766358275847715e-07, "loss": 0.1648, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.2500803571053925, "learning_rate": 1.4088335153546573e-07, "loss": 0.1784, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.24819885503338196, "learning_rate": 1.3426191327998496e-07, "loss": 0.1675, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.2437904348777516, "learning_rate": 1.277993209368744e-07, "loss": 0.16, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.24216537700757962, "learning_rate": 1.214956261808542e-07, "loss": 0.1661, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.25162221209672786, "learning_rate": 1.1535087941609846e-07, "loss": 0.1626, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.25430445297462273, "learning_rate": 1.0936512977583802e-07, "loss": 0.1802, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.24137130771241064, "learning_rate": 1.0353842512196732e-07, "loss": 0.1499, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.25716592235343155, "learning_rate": 9.787081204466253e-08, "loss": 0.1661, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2553246174339927, "learning_rate": 9.236233586200627e-08, "loss": 0.1493, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2567793872224915, "learning_rate": 8.70130406196279e-08, "loss": 0.1708, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2517911470406976, "learning_rate": 8.182296909035047e-08, "loss": 0.162, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.25782022041534747, "learning_rate": 7.679216277384439e-08, "loss": 0.1539, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.24806922088608577, "learning_rate": 7.19206618963053e-08, "loss": 0.1535, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.23972222793104037, "learning_rate": 6.720850541012347e-08, "loss": 0.1656, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.24871831127283273, "learning_rate": 6.265573099357714e-08, "loss": 0.1373, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.2580766529222835, "learning_rate": 5.826237505053067e-08, "loss": 0.1667, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.2618077265032555, "learning_rate": 5.4028472710137e-08, "loss": 0.1565, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.25144254797660864, "learning_rate": 4.9954057826571146e-08, "loss": 0.1759, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2528571616120294, "learning_rate": 4.6039162978743776e-08, "loss": 0.161, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.26189527246203287, "learning_rate": 4.228381947004812e-08, "loss": 0.1475, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.24686388092963696, "learning_rate": 3.868805732811343e-08, "loss": 0.1671, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.24627398703882258, "learning_rate": 3.525190530455636e-08, "loss": 0.1661, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.2576513241533194, "learning_rate": 3.197539087475887e-08, "loss": 0.1713, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.24681138943000402, "learning_rate": 2.8858540237641786e-08, "loss": 0.1852, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.25026250079185486, "learning_rate": 2.5901378315458247e-08, "loss": 0.1546, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.24252617911841565, "learning_rate": 2.3103928753598347e-08, "loss": 0.1795, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.2453162466753004, "learning_rate": 2.0466213920393718e-08, "loss": 0.149, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.2500829670425919, "learning_rate": 1.7988254906942115e-08, "loss": 0.1654, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.24293509162040597, "learning_rate": 1.5670071526936447e-08, "loss": 0.1526, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2636229989332803, "learning_rate": 1.3511682316509344e-08, "loss": 0.1615, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.2539431459883244, "learning_rate": 1.1513104534086605e-08, "loss": 0.1625, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.24575787540580118, "learning_rate": 9.67435416023843e-09, "loss": 0.164, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.2526104789807036, "learning_rate": 7.995445897566178e-09, "loss": 0.186, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.2583605723367482, "learning_rate": 6.476393170578021e-09, "loss": 0.1684, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.24743639056815395, "learning_rate": 5.11720812557348e-09, "loss": 0.1653, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.24733266358272377, "learning_rate": 3.917901630563492e-09, "loss": 0.1693, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2530444777520172, "learning_rate": 2.878483275170485e-09, "loss": 0.1513, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.2460400406506854, "learning_rate": 1.998961370555108e-09, "loss": 0.153, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.24934983151238052, "learning_rate": 1.2793429493518361e-09, "loss": 0.1491, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.25185967428571043, "learning_rate": 7.196337656112384e-10, "loss": 0.1347, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.27065403226515966, "learning_rate": 3.198382947511292e-10, "loss": 0.1464, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.26057612597961366, "learning_rate": 7.995973352770137e-11, "loss": 0.1581, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.23887932488439603, "learning_rate": 0.0, "loss": 0.1815, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.9732071672467948e+18, "train_loss": 0.3764596720576769, "train_runtime": 22536.0676, "train_samples_per_second": 7.011, "train_steps_per_second": 0.055 } ], "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": 1.9732071672467948e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }