{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 7.163196843167233, "learning_rate": 3.2258064516129035e-07, "loss": 1.1335, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 7.080343146604962, "learning_rate": 6.451612903225807e-07, "loss": 1.1123, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.314237276701283, "learning_rate": 9.67741935483871e-07, "loss": 1.1674, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 7.1235329864702095, "learning_rate": 1.2903225806451614e-06, "loss": 1.1295, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.630288708702644, "learning_rate": 1.6129032258064516e-06, "loss": 1.0897, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.4629476789288205, "learning_rate": 1.935483870967742e-06, "loss": 1.0749, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.301005362844269, "learning_rate": 2.2580645161290324e-06, "loss": 1.0376, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.980688000561315, "learning_rate": 2.580645161290323e-06, "loss": 1.0661, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.6877246323778086, "learning_rate": 2.903225806451613e-06, "loss": 0.9925, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.3261245473149215, "learning_rate": 3.225806451612903e-06, "loss": 0.9677, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.215466539825291, "learning_rate": 3.548387096774194e-06, "loss": 0.9705, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.30790193954055, "learning_rate": 3.870967741935484e-06, "loss": 0.9832, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.688764649584742, "learning_rate": 4.193548387096774e-06, "loss": 0.9631, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.639362460837819, "learning_rate": 4.516129032258065e-06, "loss": 0.9876, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.119219374763827, "learning_rate": 4.838709677419355e-06, "loss": 0.8985, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.142825189840269, "learning_rate": 5.161290322580646e-06, "loss": 0.9421, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 3.0439247111690104, "learning_rate": 5.483870967741935e-06, "loss": 0.926, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.7321318547326516, "learning_rate": 5.806451612903226e-06, "loss": 0.9062, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.263437316896479, "learning_rate": 6.129032258064517e-06, "loss": 0.8592, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.7519540251137555, "learning_rate": 6.451612903225806e-06, "loss": 0.8422, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.6746344295636064, "learning_rate": 6.774193548387097e-06, "loss": 0.8368, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.9861137104039042, "learning_rate": 7.096774193548388e-06, "loss": 0.84, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.777224089381116, "learning_rate": 7.4193548387096784e-06, "loss": 0.822, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.6507330485168512, "learning_rate": 7.741935483870968e-06, "loss": 0.8349, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.2432071089953725, "learning_rate": 8.064516129032258e-06, "loss": 0.7864, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.2788376094889264, "learning_rate": 8.387096774193549e-06, "loss": 0.796, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.3018251221242503, "learning_rate": 8.70967741935484e-06, "loss": 0.8156, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.0814451160934697, "learning_rate": 9.03225806451613e-06, "loss": 0.7836, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.026180540866377, "learning_rate": 9.35483870967742e-06, "loss": 0.8513, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.980371632559978, "learning_rate": 9.67741935483871e-06, "loss": 0.7664, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.978253746149384, "learning_rate": 1e-05, "loss": 0.7927, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.9389765695454946, "learning_rate": 1.0322580645161291e-05, "loss": 0.757, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.8827267011044461, "learning_rate": 1.0645161290322582e-05, "loss": 0.7669, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.8641342769633925, "learning_rate": 1.096774193548387e-05, "loss": 0.7541, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.889919651314729, "learning_rate": 1.1290322580645164e-05, "loss": 0.7974, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.8165567889373015, "learning_rate": 1.1612903225806453e-05, "loss": 0.7971, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.7332721859097205, "learning_rate": 1.1935483870967743e-05, "loss": 0.7439, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.7908114910444407, "learning_rate": 1.2258064516129034e-05, "loss": 0.7573, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.9009813738262911, "learning_rate": 1.2580645161290324e-05, "loss": 0.7414, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.7642370905028689, "learning_rate": 1.2903225806451613e-05, "loss": 0.728, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7556244079332577, "learning_rate": 1.3225806451612903e-05, "loss": 0.754, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.7767928715488234, "learning_rate": 1.3548387096774194e-05, "loss": 0.7587, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.7705108364153264, "learning_rate": 1.3870967741935486e-05, "loss": 0.7344, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6374910106743598, "learning_rate": 1.4193548387096776e-05, "loss": 0.7265, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.7178461939241406, "learning_rate": 1.4516129032258066e-05, "loss": 0.7417, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.8584636538844731, "learning_rate": 1.4838709677419357e-05, "loss": 0.7545, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.8586106334114252, "learning_rate": 1.5161290322580646e-05, "loss": 0.7574, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.8725067413123165, "learning_rate": 1.5483870967741936e-05, "loss": 0.7423, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.7368455958741041, "learning_rate": 1.5806451612903226e-05, "loss": 0.7406, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.9152279117286702, "learning_rate": 1.6129032258064517e-05, "loss": 0.7098, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.9481903762386144, "learning_rate": 1.6451612903225807e-05, "loss": 0.7435, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.878895135730166, "learning_rate": 1.6774193548387098e-05, "loss": 0.723, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.8351090514531875, "learning_rate": 1.7096774193548388e-05, "loss": 0.7161, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.8187905628171753, "learning_rate": 1.741935483870968e-05, "loss": 0.7299, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.818607357568121, "learning_rate": 1.774193548387097e-05, "loss": 0.752, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6404160970772527, "learning_rate": 1.806451612903226e-05, "loss": 0.7136, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.7131367629069327, "learning_rate": 1.838709677419355e-05, "loss": 0.7367, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.7408196464583737, "learning_rate": 1.870967741935484e-05, "loss": 0.7419, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.6852763345871823, "learning_rate": 1.903225806451613e-05, "loss": 0.7576, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.7432748556496063, "learning_rate": 1.935483870967742e-05, "loss": 0.7444, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.6949822016384513, "learning_rate": 1.967741935483871e-05, "loss": 0.7491, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.7304067448545818, "learning_rate": 2e-05, "loss": 0.7123, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5827919951428059, "learning_rate": 2.0322580645161292e-05, "loss": 0.6931, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7030551162511721, "learning_rate": 2.0645161290322582e-05, "loss": 0.7327, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.7258063255458705, "learning_rate": 2.0967741935483873e-05, "loss": 0.73, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6492420285666961, "learning_rate": 2.1290322580645163e-05, "loss": 0.7127, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7873303438853297, "learning_rate": 2.161290322580645e-05, "loss": 0.7441, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.6183250176354177, "learning_rate": 2.193548387096774e-05, "loss": 0.7195, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.7365197288488894, "learning_rate": 2.225806451612903e-05, "loss": 0.7222, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.706153362053349, "learning_rate": 2.2580645161290328e-05, "loss": 0.7137, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.6796399968472113, "learning_rate": 2.2903225806451615e-05, "loss": 0.7076, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.727587663334609, "learning_rate": 2.3225806451612906e-05, "loss": 0.7133, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.8765721905470469, "learning_rate": 2.3548387096774196e-05, "loss": 0.7107, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.8253696353988064, "learning_rate": 2.3870967741935486e-05, "loss": 0.7426, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.7457509266663693, "learning_rate": 2.4193548387096777e-05, "loss": 0.7225, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.7452260427378244, "learning_rate": 2.4516129032258067e-05, "loss": 0.7318, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.6997018491765974, "learning_rate": 2.4838709677419358e-05, "loss": 0.682, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7709605531507131, "learning_rate": 2.5161290322580648e-05, "loss": 0.7478, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7565988139172697, "learning_rate": 2.548387096774194e-05, "loss": 0.7235, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.8141258677167093, "learning_rate": 2.5806451612903226e-05, "loss": 0.6822, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.7719873397141351, "learning_rate": 2.6129032258064516e-05, "loss": 0.7283, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.8258070952853007, "learning_rate": 2.6451612903225806e-05, "loss": 0.7251, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.7883724512709737, "learning_rate": 2.6774193548387097e-05, "loss": 0.7126, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.8449248320615658, "learning_rate": 2.7096774193548387e-05, "loss": 0.7182, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.6872154361790026, "learning_rate": 2.7419354838709678e-05, "loss": 0.6949, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7911379702536034, "learning_rate": 2.774193548387097e-05, "loss": 0.6888, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.6887352247232339, "learning_rate": 2.8064516129032262e-05, "loss": 0.6768, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.9151210023910717, "learning_rate": 2.8387096774193552e-05, "loss": 0.7257, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.8230957871885821, "learning_rate": 2.8709677419354843e-05, "loss": 0.7075, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7480304338313394, "learning_rate": 2.9032258064516133e-05, "loss": 0.6699, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.8199583841831843, "learning_rate": 2.9354838709677423e-05, "loss": 0.6901, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.7202223990807257, "learning_rate": 2.9677419354838714e-05, "loss": 0.6924, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.77660915375571, "learning_rate": 3.0000000000000004e-05, "loss": 0.6802, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7505220012197329, "learning_rate": 3.032258064516129e-05, "loss": 0.732, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.7461761142627008, "learning_rate": 3.0645161290322585e-05, "loss": 0.7201, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.7111084296090587, "learning_rate": 3.096774193548387e-05, "loss": 0.6815, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.6524455760832287, "learning_rate": 3.1290322580645166e-05, "loss": 0.6875, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.7220938368650478, "learning_rate": 3.161290322580645e-05, "loss": 0.6855, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.8609471076773013, "learning_rate": 3.193548387096774e-05, "loss": 0.7158, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.7942749695479527, "learning_rate": 3.2258064516129034e-05, "loss": 0.7048, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.7813989831427528, "learning_rate": 3.258064516129033e-05, "loss": 0.6797, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.999292973020803, "learning_rate": 3.2903225806451614e-05, "loss": 0.6996, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.9659043674613157, "learning_rate": 3.322580645161291e-05, "loss": 0.7125, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.7988934482718741, "learning_rate": 3.3548387096774195e-05, "loss": 0.7123, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.0361399408238539, "learning_rate": 3.387096774193549e-05, "loss": 0.6773, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.0573359515313496, "learning_rate": 3.4193548387096776e-05, "loss": 0.6754, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.9111629558265176, "learning_rate": 3.451612903225807e-05, "loss": 0.6848, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.91464584544994, "learning_rate": 3.483870967741936e-05, "loss": 0.7093, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9024541603238685, "learning_rate": 3.516129032258065e-05, "loss": 0.6964, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.7557018960403143, "learning_rate": 3.548387096774194e-05, "loss": 0.7108, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.0659996702038417, "learning_rate": 3.5806451612903225e-05, "loss": 0.7347, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.7679091337820259, "learning_rate": 3.612903225806452e-05, "loss": 0.6969, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.8646981981978001, "learning_rate": 3.6451612903225805e-05, "loss": 0.7307, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.014956637880936, "learning_rate": 3.67741935483871e-05, "loss": 0.7035, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.8961079582706198, "learning_rate": 3.7096774193548386e-05, "loss": 0.6626, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.694511997461011, "learning_rate": 3.741935483870968e-05, "loss": 0.6829, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.8585748332921243, "learning_rate": 3.7741935483870974e-05, "loss": 0.6779, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.9873766879674759, "learning_rate": 3.806451612903226e-05, "loss": 0.7297, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.7200783963606526, "learning_rate": 3.8387096774193555e-05, "loss": 0.6929, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.9669399242810096, "learning_rate": 3.870967741935484e-05, "loss": 0.6954, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.8524668373949869, "learning_rate": 3.9032258064516135e-05, "loss": 0.6809, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6581438488945158, "learning_rate": 3.935483870967742e-05, "loss": 0.689, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7896328609074594, "learning_rate": 3.9677419354838716e-05, "loss": 0.7105, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7075388976265357, "learning_rate": 4e-05, "loss": 0.6858, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.6856946090706645, "learning_rate": 3.9999920040266474e-05, "loss": 0.7043, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.6851004942064105, "learning_rate": 3.999968016170525e-05, "loss": 0.6851, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.7948028282650483, "learning_rate": 3.9999280366234394e-05, "loss": 0.7305, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.8920672440058268, "learning_rate": 3.999872065705065e-05, "loss": 0.7002, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.7092080853677435, "learning_rate": 3.999800103862945e-05, "loss": 0.681, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6895784638616415, "learning_rate": 3.9997121516724834e-05, "loss": 0.7067, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.7826919739520227, "learning_rate": 3.999608209836944e-05, "loss": 0.7149, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.6967650524071034, "learning_rate": 3.999488279187443e-05, "loss": 0.6654, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.7083181063772209, "learning_rate": 3.9993523606829425e-05, "loss": 0.6826, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.6858959596006989, "learning_rate": 3.9992004554102435e-05, "loss": 0.7347, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7756914648754059, "learning_rate": 3.999032564583976e-05, "loss": 0.7006, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.6426193991666975, "learning_rate": 3.998848689546591e-05, "loss": 0.7001, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.6889500922735152, "learning_rate": 3.9986488317683496e-05, "loss": 0.7044, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.7385051624842369, "learning_rate": 3.9984329928473067e-05, "loss": 0.7157, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.7421579526510442, "learning_rate": 3.998201174509306e-05, "loss": 0.7131, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.9861225421956132, "learning_rate": 3.997953378607961e-05, "loss": 0.6641, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.7084724000130537, "learning_rate": 3.9976896071246403e-05, "loss": 0.6748, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.946540040752946, "learning_rate": 3.997409862168454e-05, "loss": 0.6694, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.058954727098601, "learning_rate": 3.997114145976237e-05, "loss": 0.7172, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.8705146545848983, "learning_rate": 3.9968024609125245e-05, "loss": 0.725, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7881591814947245, "learning_rate": 3.996474809469545e-05, "loss": 0.6688, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.8037611943766985, "learning_rate": 3.996131194267189e-05, "loss": 0.6711, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.8465688776987551, "learning_rate": 3.995771618052995e-05, "loss": 0.714, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.6842684279687982, "learning_rate": 3.9953960837021256e-05, "loss": 0.7053, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7675883687277776, "learning_rate": 3.995004594217343e-05, "loss": 0.7184, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7062865432819683, "learning_rate": 3.994597152728987e-05, "loss": 0.7139, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.7728785314431947, "learning_rate": 3.994173762494947e-05, "loss": 0.732, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.7506600719195518, "learning_rate": 3.9937344269006424e-05, "loss": 0.6972, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7495922816182294, "learning_rate": 3.993279149458988e-05, "loss": 0.684, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.755616918674353, "learning_rate": 3.9928079338103695e-05, "loss": 0.6533, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.7905282540478201, "learning_rate": 3.992320783722616e-05, "loss": 0.7023, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.9706459974685454, "learning_rate": 3.991817703090965e-05, "loss": 0.7222, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.7943030253916452, "learning_rate": 3.991298695938038e-05, "loss": 0.7061, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.992776189257943, "learning_rate": 3.9907637664138e-05, "loss": 0.6933, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7148219390739902, "learning_rate": 3.990212918795534e-05, "loss": 0.6818, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.8204977641953565, "learning_rate": 3.9896461574878036e-05, "loss": 0.6778, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.8711632144404708, "learning_rate": 3.989063487022416e-05, "loss": 0.7384, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.7653366365538992, "learning_rate": 3.9884649120583903e-05, "loss": 0.6717, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.9132347619469875, "learning_rate": 3.987850437381915e-05, "loss": 0.6936, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6707305289884553, "learning_rate": 3.987220067906313e-05, "loss": 0.6818, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.7786056765742505, "learning_rate": 3.986573808672002e-05, "loss": 0.655, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.5851760889756351, "learning_rate": 3.9859116648464534e-05, "loss": 0.6848, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.828625717119132, "learning_rate": 3.985233641724152e-05, "loss": 0.6812, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7172967869580603, "learning_rate": 3.984539744726554e-05, "loss": 0.6793, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.9324541382527197, "learning_rate": 3.983829979402038e-05, "loss": 0.6609, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.7299745892570279, "learning_rate": 3.983104351425871e-05, "loss": 0.6854, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7724081069945671, "learning_rate": 3.982362866600154e-05, "loss": 0.664, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.909504449265301, "learning_rate": 3.9816055308537806e-05, "loss": 0.6544, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.6332751877696399, "learning_rate": 3.980832350242388e-05, "loss": 0.7055, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.7809424101292393, "learning_rate": 3.980043330948306e-05, "loss": 0.6528, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.617705913201517, "learning_rate": 3.9792384792805124e-05, "loss": 0.6735, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.7123380773573281, "learning_rate": 3.978417801674579e-05, "loss": 0.6946, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.7505426100921293, "learning_rate": 3.9775813046926244e-05, "loss": 0.7172, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6392598842014838, "learning_rate": 3.976728995023254e-05, "loss": 0.7036, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.711335637675252, "learning_rate": 3.975860879481514e-05, "loss": 0.6365, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.7282509587254435, "learning_rate": 3.974976965008833e-05, "loss": 0.6935, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.7882671731721596, "learning_rate": 3.9740772586729674e-05, "loss": 0.6951, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.7521126318778882, "learning_rate": 3.973161767667946e-05, "loss": 0.6764, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6692793938367949, "learning_rate": 3.972230499314009e-05, "loss": 0.6987, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.8485434312611156, "learning_rate": 3.9712834610575545e-05, "loss": 0.6988, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5088532818015894, "learning_rate": 3.9703206604710746e-05, "loss": 0.6447, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.8774950721194834, "learning_rate": 3.969342105253098e-05, "loss": 0.6998, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.7576761639618439, "learning_rate": 3.9683478032281246e-05, "loss": 0.701, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.6063928341484288, "learning_rate": 3.967337762346568e-05, "loss": 0.6479, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.7140304831165453, "learning_rate": 3.9663119906846885e-05, "loss": 0.6609, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.6061078364695947, "learning_rate": 3.965270496444528e-05, "loss": 0.686, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6259131570165186, "learning_rate": 3.9642132879538465e-05, "loss": 0.7011, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.62417133005836, "learning_rate": 3.9631403736660566e-05, "loss": 0.677, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5660510206098045, "learning_rate": 3.962051762160151e-05, "loss": 0.7012, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.7230589555140007, "learning_rate": 3.960947462140638e-05, "loss": 0.6514, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5289444306877069, "learning_rate": 3.959827482437472e-05, "loss": 0.6713, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.7563216468662158, "learning_rate": 3.958691832005981e-05, "loss": 0.7111, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5722986284367741, "learning_rate": 3.9575405199267944e-05, "loss": 0.6468, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.5478994386479475, "learning_rate": 3.956373555405774e-05, "loss": 0.6679, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6068207149145805, "learning_rate": 3.955190947773937e-05, "loss": 0.6677, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.6312965741514812, "learning_rate": 3.9539927064873824e-05, "loss": 0.6984, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6903415624861889, "learning_rate": 3.952778841127214e-05, "loss": 0.7118, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5729277073724046, "learning_rate": 3.95154936139947e-05, "loss": 0.6656, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.6699487930772537, "learning_rate": 3.950304277135034e-05, "loss": 0.655, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.8727607876232395, "learning_rate": 3.94904359828957e-05, "loss": 0.6722, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5814104107822167, "learning_rate": 3.94776733494343e-05, "loss": 0.6785, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.8036999556206147, "learning_rate": 3.9464754973015826e-05, "loss": 0.6933, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.6123739204614637, "learning_rate": 3.9451680956935275e-05, "loss": 0.6713, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.655357003546718, "learning_rate": 3.943845140573213e-05, "loss": 0.6773, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.6405033729830898, "learning_rate": 3.942506642518952e-05, "loss": 0.6528, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.6072373272991894, "learning_rate": 3.9411526122333396e-05, "loss": 0.6795, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.6587586095192662, "learning_rate": 3.939783060543167e-05, "loss": 0.6866, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5784417376017005, "learning_rate": 3.938397998399333e-05, "loss": 0.6692, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6479265464682589, "learning_rate": 3.936997436876756e-05, "loss": 0.6744, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6944897923550684, "learning_rate": 3.935581387174289e-05, "loss": 0.697, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.6030183270142285, "learning_rate": 3.9341498606146295e-05, "loss": 0.6908, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.7455523271211218, "learning_rate": 3.932702868644224e-05, "loss": 0.6844, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.6470993729049328, "learning_rate": 3.931240422833181e-05, "loss": 0.6959, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7013256389394597, "learning_rate": 3.9297625348751806e-05, "loss": 0.6483, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.6240032838794349, "learning_rate": 3.9282692165873744e-05, "loss": 0.6409, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.6498066620375346, "learning_rate": 3.9267604799102945e-05, "loss": 0.6771, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.6839214593594298, "learning_rate": 3.9252363369077615e-05, "loss": 0.6639, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.6037483146115686, "learning_rate": 3.9236967997667796e-05, "loss": 0.6836, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.6612377783859475, "learning_rate": 3.9221418807974496e-05, "loss": 0.6608, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.7026835785264076, "learning_rate": 3.92057159243286e-05, "loss": 0.6899, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.7251131519722142, "learning_rate": 3.9189859472289956e-05, "loss": 0.6967, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.8127556188629222, "learning_rate": 3.9173849578646324e-05, "loss": 0.6805, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.7689731178127424, "learning_rate": 3.9157686371412395e-05, "loss": 0.6949, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.7250039642768668, "learning_rate": 3.914136997982874e-05, "loss": 0.7173, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.7277630897909, "learning_rate": 3.912490053436079e-05, "loss": 0.6913, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5785568824253037, "learning_rate": 3.9108278166697805e-05, "loss": 0.6342, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.7381618028409163, "learning_rate": 3.909150300975178e-05, "loss": 0.672, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.648920388475064, "learning_rate": 3.907457519765642e-05, "loss": 0.6381, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5802944028003566, "learning_rate": 3.905749486576607e-05, "loss": 0.67, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.7129040729740911, "learning_rate": 3.90402621506546e-05, "loss": 0.6358, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.6210786623333788, "learning_rate": 3.902287719011435e-05, "loss": 0.6634, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.8083702209422521, "learning_rate": 3.900534012315499e-05, "loss": 0.6877, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.7135688380689069, "learning_rate": 3.8987651090002454e-05, "loss": 0.7036, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.6627456838450434, "learning_rate": 3.896981023209777e-05, "loss": 0.6394, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.6567543097504123, "learning_rate": 3.8951817692095966e-05, "loss": 0.6467, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5484293899143656, "learning_rate": 3.893367361386491e-05, "loss": 0.6644, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.7016759243324949, "learning_rate": 3.891537814248417e-05, "loss": 0.6699, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.6705186487373144, "learning_rate": 3.889693142424384e-05, "loss": 0.6796, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.7340411032018733, "learning_rate": 3.8878333606643405e-05, "loss": 0.6535, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6077898886032025, "learning_rate": 3.885958483839049e-05, "loss": 0.6916, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.8456529763776653, "learning_rate": 3.8840685269399786e-05, "loss": 0.6916, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.5557666587968039, "learning_rate": 3.882163505079171e-05, "loss": 0.6843, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.839699068292205, "learning_rate": 3.880243433489132e-05, "loss": 0.6843, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.7775177533981861, "learning_rate": 3.878308327522702e-05, "loss": 0.5752, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.6490343034359954, "learning_rate": 3.876358202652936e-05, "loss": 0.5273, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.7687748058018673, "learning_rate": 3.8743930744729835e-05, "loss": 0.5645, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.7021053126687874, "learning_rate": 3.8724129586959535e-05, "loss": 0.539, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.7820075819023818, "learning_rate": 3.870417871154801e-05, "loss": 0.521, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6274692123283909, "learning_rate": 3.868407827802192e-05, "loss": 0.5312, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.8552113204040772, "learning_rate": 3.8663828447103804e-05, "loss": 0.5686, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6920945733923451, "learning_rate": 3.8643429380710765e-05, "loss": 0.552, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.7788565146614175, "learning_rate": 3.862288124195319e-05, "loss": 0.5185, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.7134735746914184, "learning_rate": 3.8602184195133464e-05, "loss": 0.554, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.6937914820866413, "learning_rate": 3.8581338405744604e-05, "loss": 0.5377, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.7125773796640845, "learning_rate": 3.8560344040468996e-05, "loss": 0.5552, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.8316473644721323, "learning_rate": 3.853920126717703e-05, "loss": 0.5518, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.7020632414353107, "learning_rate": 3.851791025492574e-05, "loss": 0.5306, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.7682993834307025, "learning_rate": 3.8496471173957515e-05, "loss": 0.5671, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.6342514245889219, "learning_rate": 3.847488419569866e-05, "loss": 0.5233, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.7573751630458482, "learning_rate": 3.8453149492758077e-05, "loss": 0.5249, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.7986288545431922, "learning_rate": 3.8431267238925886e-05, "loss": 0.5196, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.7431363748276332, "learning_rate": 3.840923760917199e-05, "loss": 0.5473, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.7309657112817599, "learning_rate": 3.838706077964473e-05, "loss": 0.5269, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.6599628028461176, "learning_rate": 3.836473692766944e-05, "loss": 0.5042, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5649456396657231, "learning_rate": 3.834226623174705e-05, "loss": 0.5638, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.6882141140699898, "learning_rate": 3.831964887155264e-05, "loss": 0.5394, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6518000322724598, "learning_rate": 3.829688502793403e-05, "loss": 0.536, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.6916197504676003, "learning_rate": 3.827397488291029e-05, "loss": 0.5419, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.6832472087548521, "learning_rate": 3.8250918619670343e-05, "loss": 0.5363, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.6187133530506638, "learning_rate": 3.822771642257145e-05, "loss": 0.54, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.6258863729121829, "learning_rate": 3.820436847713776e-05, "loss": 0.5143, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.5252624222993494, "learning_rate": 3.8180874970058826e-05, "loss": 0.4968, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.7662400842792145, "learning_rate": 3.8157236089188103e-05, "loss": 0.5395, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.60754019664639, "learning_rate": 3.813345202354145e-05, "loss": 0.555, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6911767198751007, "learning_rate": 3.810952296329563e-05, "loss": 0.5289, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.5961436856520005, "learning_rate": 3.808544909978676e-05, "loss": 0.5268, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.8104092597312106, "learning_rate": 3.806123062550882e-05, "loss": 0.5529, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.690165351656133, "learning_rate": 3.803686773411208e-05, "loss": 0.5283, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.5832658693350826, "learning_rate": 3.801236062040158e-05, "loss": 0.5403, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.6272191370475715, "learning_rate": 3.798770948033553e-05, "loss": 0.5195, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5336604775566612, "learning_rate": 3.796291451102381e-05, "loss": 0.5319, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6183916039382475, "learning_rate": 3.793797591072631e-05, "loss": 0.5237, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6079460181722497, "learning_rate": 3.791289387885144e-05, "loss": 0.5388, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.631744210433808, "learning_rate": 3.788766861595443e-05, "loss": 0.5348, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.6194690513019571, "learning_rate": 3.7862300323735835e-05, "loss": 0.5479, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5747375862024741, "learning_rate": 3.783678920503983e-05, "loss": 0.5051, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.6670824260644573, "learning_rate": 3.781113546385265e-05, "loss": 0.503, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.6281559096739433, "learning_rate": 3.7785339305300916e-05, "loss": 0.5376, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6673291802114116, "learning_rate": 3.7759400935650025e-05, "loss": 0.5286, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5373893920746294, "learning_rate": 3.77333205623025e-05, "loss": 0.5545, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.738547530574742, "learning_rate": 3.7707098393796295e-05, "loss": 0.5443, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.6348255899621187, "learning_rate": 3.7680734639803185e-05, "loss": 0.5161, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.6560234324268818, "learning_rate": 3.765422951112704e-05, "loss": 0.5576, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.7295298903814891, "learning_rate": 3.762758321970216e-05, "loss": 0.5067, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.6170856001186874, "learning_rate": 3.7600795978591584e-05, "loss": 0.5288, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.6111075940227949, "learning_rate": 3.757386800198538e-05, "loss": 0.5702, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.6299565875307201, "learning_rate": 3.7546799505198925e-05, "loss": 0.5687, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.6085090896749991, "learning_rate": 3.7519590704671197e-05, "loss": 0.54, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5391307238262271, "learning_rate": 3.749224181796305e-05, "loss": 0.5177, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.6516186576889232, "learning_rate": 3.746475306375545e-05, "loss": 0.5507, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5229959142192903, "learning_rate": 3.743712466184774e-05, "loss": 0.5452, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.6420774457649235, "learning_rate": 3.7409356833155885e-05, "loss": 0.5368, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.5706066034647025, "learning_rate": 3.73814497997107e-05, "loss": 0.5278, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.6438239783504113, "learning_rate": 3.7353403784656095e-05, "loss": 0.537, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.6900366630344852, "learning_rate": 3.732521901224724e-05, "loss": 0.534, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6281955140542639, "learning_rate": 3.7296895707848844e-05, "loss": 0.5051, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.6460920890876138, "learning_rate": 3.7268434097933275e-05, "loss": 0.5292, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.5969263920875383, "learning_rate": 3.723983441007882e-05, "loss": 0.5425, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5477836132954683, "learning_rate": 3.721109687296781e-05, "loss": 0.5472, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.6593578337753195, "learning_rate": 3.718222171638484e-05, "loss": 0.5551, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.6020514379359302, "learning_rate": 3.715320917121488e-05, "loss": 0.5535, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.5861973927070746, "learning_rate": 3.712405946944149e-05, "loss": 0.5388, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.61497834514705, "learning_rate": 3.709477284414488e-05, "loss": 0.5656, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.5564872853940956, "learning_rate": 3.7065349529500136e-05, "loss": 0.5479, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.6108023446460215, "learning_rate": 3.7035789760775305e-05, "loss": 0.5189, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.55544970500314, "learning_rate": 3.70060937743295e-05, "loss": 0.5303, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.646615878850501, "learning_rate": 3.6976261807611045e-05, "loss": 0.5291, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.7070384902306223, "learning_rate": 3.694629409915555e-05, "loss": 0.5732, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6896430857422295, "learning_rate": 3.691619088858401e-05, "loss": 0.5468, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.6797599529906256, "learning_rate": 3.68859524166009e-05, "loss": 0.5288, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.5200621714178325, "learning_rate": 3.6855578924992226e-05, "loss": 0.5258, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.9062391558728455, "learning_rate": 3.6825070656623626e-05, "loss": 0.5403, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.5918030829615106, "learning_rate": 3.67944278554384e-05, "loss": 0.5418, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.6745253084423186, "learning_rate": 3.676365076645557e-05, "loss": 0.5209, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.5717211808346903, "learning_rate": 3.673273963576791e-05, "loss": 0.5, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6352692959727557, "learning_rate": 3.670169471054001e-05, "loss": 0.5499, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.5851913823230566, "learning_rate": 3.6670516239006254e-05, "loss": 0.5454, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.56491427899946, "learning_rate": 3.663920447046888e-05, "loss": 0.5289, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.6021499219774271, "learning_rate": 3.6607759655295954e-05, "loss": 0.5357, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5297759953922088, "learning_rate": 3.657618204491937e-05, "loss": 0.5246, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.6885684498405749, "learning_rate": 3.6544471891832875e-05, "loss": 0.5465, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.5563273246516361, "learning_rate": 3.6512629449589983e-05, "loss": 0.5367, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.8442627243891159, "learning_rate": 3.6480654972802045e-05, "loss": 0.5442, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5668740446942515, "learning_rate": 3.644854871713611e-05, "loss": 0.5546, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.5866946155330355, "learning_rate": 3.6416310939312924e-05, "loss": 0.5241, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.6076483826048339, "learning_rate": 3.638394189710493e-05, "loss": 0.4954, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.569491599340188, "learning_rate": 3.635144184933412e-05, "loss": 0.523, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.578841155105816, "learning_rate": 3.6318811055869994e-05, "loss": 0.55, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.6110106266897211, "learning_rate": 3.628604977762752e-05, "loss": 0.5475, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.5566058122464308, "learning_rate": 3.6253158276565004e-05, "loss": 0.5313, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.6265745523075971, "learning_rate": 3.6220136815682016e-05, "loss": 0.57, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.5638411141466748, "learning_rate": 3.618698565901727e-05, "loss": 0.5436, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.5394209683889928, "learning_rate": 3.615370507164654e-05, "loss": 0.531, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5880816990314646, "learning_rate": 3.61202953196805e-05, "loss": 0.5357, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5118768202144897, "learning_rate": 3.6086756670262654e-05, "loss": 0.5396, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.5767371801029573, "learning_rate": 3.6053089391567135e-05, "loss": 0.5353, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.5106469285721685, "learning_rate": 3.601929375279662e-05, "loss": 0.5043, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.5392146846859385, "learning_rate": 3.598537002418012e-05, "loss": 0.5494, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.5552347368537064, "learning_rate": 3.5951318476970885e-05, "loss": 0.5631, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5981152227503705, "learning_rate": 3.591713938344416e-05, "loss": 0.5444, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.598070469564046, "learning_rate": 3.588283301689507e-05, "loss": 0.536, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.49755647763716, "learning_rate": 3.5848399651636424e-05, "loss": 0.5268, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.6208893767702673, "learning_rate": 3.5813839562996473e-05, "loss": 0.5609, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.4921515896507513, "learning_rate": 3.5779153027316775e-05, "loss": 0.5432, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.5614152719043732, "learning_rate": 3.574434032194994e-05, "loss": 0.5447, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.5067383030531077, "learning_rate": 3.5709401725257436e-05, "loss": 0.5548, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.5207048598251552, "learning_rate": 3.5674337516607346e-05, "loss": 0.5212, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5362598449993783, "learning_rate": 3.563914797637216e-05, "loss": 0.5279, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5801741125463558, "learning_rate": 3.560383338592649e-05, "loss": 0.5551, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.6304678315161377, "learning_rate": 3.556839402764487e-05, "loss": 0.5668, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.6096569948808216, "learning_rate": 3.553283018489946e-05, "loss": 0.5465, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5835424811449795, "learning_rate": 3.54971421420578e-05, "loss": 0.5441, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.6284905616896523, "learning_rate": 3.5461330184480524e-05, "loss": 0.5143, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.5139789435347629, "learning_rate": 3.54253945985191e-05, "loss": 0.5294, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.6311330064759008, "learning_rate": 3.5389335671513524e-05, "loss": 0.5361, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.5260308208399034, "learning_rate": 3.5353153691789986e-05, "loss": 0.5612, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.5261219684095582, "learning_rate": 3.531684894865866e-05, "loss": 0.5562, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.6585179000533864, "learning_rate": 3.528042173241128e-05, "loss": 0.518, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.5367867945743908, "learning_rate": 3.524387233431892e-05, "loss": 0.5289, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.6250002121623552, "learning_rate": 3.520720104662958e-05, "loss": 0.5267, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.5661160325366438, "learning_rate": 3.5170408162565904e-05, "loss": 0.5491, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.5517786893518769, "learning_rate": 3.513349397632281e-05, "loss": 0.5494, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.5809013087665439, "learning_rate": 3.5096458783065145e-05, "loss": 0.5427, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5609588754051357, "learning_rate": 3.505930287892533e-05, "loss": 0.5303, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.570015446025097, "learning_rate": 3.502202656100099e-05, "loss": 0.5609, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5895047565705419, "learning_rate": 3.498463012735256e-05, "loss": 0.5516, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.5775816407355224, "learning_rate": 3.494711387700094e-05, "loss": 0.5463, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.4891651823568343, "learning_rate": 3.490947810992505e-05, "loss": 0.5254, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.590667388648427, "learning_rate": 3.48717231270595e-05, "loss": 0.531, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.48180746978768935, "learning_rate": 3.483384923029211e-05, "loss": 0.5243, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.5303861212711827, "learning_rate": 3.479585672246156e-05, "loss": 0.5378, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.6118004448636181, "learning_rate": 3.4757745907354924e-05, "loss": 0.5429, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4743627665578491, "learning_rate": 3.471951708970527e-05, "loss": 0.5318, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.6128219914041109, "learning_rate": 3.468117057518921e-05, "loss": 0.521, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.49379804461937016, "learning_rate": 3.4642706670424426e-05, "loss": 0.54, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.5121677778652661, "learning_rate": 3.460412568296731e-05, "loss": 0.5366, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.5482369768487256, "learning_rate": 3.456542792131039e-05, "loss": 0.5436, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.5126424882212807, "learning_rate": 3.4526613694879936e-05, "loss": 0.5513, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.575102785418558, "learning_rate": 3.448768331403348e-05, "loss": 0.5364, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.5239257182795439, "learning_rate": 3.44486370900573e-05, "loss": 0.526, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.5870464417738448, "learning_rate": 3.440947533516396e-05, "loss": 0.5472, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.5729914230480165, "learning_rate": 3.4370198362489816e-05, "loss": 0.5793, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.5995464594246805, "learning_rate": 3.43308064860925e-05, "loss": 0.5577, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5697751833768416, "learning_rate": 3.4291300020948393e-05, "loss": 0.5097, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.537010896456718, "learning_rate": 3.425167928295015e-05, "loss": 0.5376, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.5272634539188191, "learning_rate": 3.421194458890411e-05, "loss": 0.5054, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.6569081610004496, "learning_rate": 3.4172096256527865e-05, "loss": 0.5206, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5588103613461504, "learning_rate": 3.4132134604447595e-05, "loss": 0.5535, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.70243736931057, "learning_rate": 3.409205995219561e-05, "loss": 0.5528, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.5375389365362732, "learning_rate": 3.4051872620207765e-05, "loss": 0.535, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.5544457377354168, "learning_rate": 3.40115729298209e-05, "loss": 0.5195, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.5704236575207574, "learning_rate": 3.397116120327025e-05, "loss": 0.543, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.5564350659795477, "learning_rate": 3.3930637763686916e-05, "loss": 0.5628, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.6089515379265635, "learning_rate": 3.389000293509524e-05, "loss": 0.5419, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5270323097795511, "learning_rate": 3.3849257042410225e-05, "loss": 0.5499, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5536814938059514, "learning_rate": 3.380840041143494e-05, "loss": 0.513, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.6182460761919965, "learning_rate": 3.376743336885792e-05, "loss": 0.5468, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.533017053296401, "learning_rate": 3.372635624225055e-05, "loss": 0.5343, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.6394052048643603, "learning_rate": 3.3685169360064445e-05, "loss": 0.5316, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.5043872163748262, "learning_rate": 3.3643873051628804e-05, "loss": 0.5159, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.5682363797762209, "learning_rate": 3.3602467647147814e-05, "loss": 0.546, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.5683497990643029, "learning_rate": 3.356095347769799e-05, "loss": 0.5517, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.5008228575099645, "learning_rate": 3.351933087522552e-05, "loss": 0.5139, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.5824985901718199, "learning_rate": 3.3477600172543626e-05, "loss": 0.5342, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.5402865764885615, "learning_rate": 3.3435761703329894e-05, "loss": 0.5317, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.5005556954965564, "learning_rate": 3.3393815802123606e-05, "loss": 0.5306, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.5301620641610845, "learning_rate": 3.335176280432308e-05, "loss": 0.5264, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.49854357765262786, "learning_rate": 3.330960304618295e-05, "loss": 0.5358, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.5189251595288058, "learning_rate": 3.326733686481153e-05, "loss": 0.5344, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.5249489441964577, "learning_rate": 3.3224964598168084e-05, "loss": 0.551, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.528821755959493, "learning_rate": 3.318248658506012e-05, "loss": 0.5128, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.5054648436815533, "learning_rate": 3.313990316514069e-05, "loss": 0.5245, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.6112819816097972, "learning_rate": 3.309721467890571e-05, "loss": 0.5299, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.5809185124448435, "learning_rate": 3.305442146769115e-05, "loss": 0.5645, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.5321442829448472, "learning_rate": 3.30115238736704e-05, "loss": 0.5177, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.5339545516715187, "learning_rate": 3.296852223985148e-05, "loss": 0.5515, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.5267088314805602, "learning_rate": 3.2925416910074315e-05, "loss": 0.5102, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.5018918944457808, "learning_rate": 3.288220822900796e-05, "loss": 0.5413, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.5159709989848261, "learning_rate": 3.283889654214788e-05, "loss": 0.5207, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.5194503698983456, "learning_rate": 3.279548219581317e-05, "loss": 0.546, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.5262022438068126, "learning_rate": 3.275196553714379e-05, "loss": 0.5371, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.4906422884248544, "learning_rate": 3.270834691409778e-05, "loss": 0.5294, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.503423627538387, "learning_rate": 3.266462667544849e-05, "loss": 0.5295, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.49354134558241497, "learning_rate": 3.262080517078178e-05, "loss": 0.5367, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.5165965130754271, "learning_rate": 3.257688275049323e-05, "loss": 0.5545, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.5128080760079655, "learning_rate": 3.253285976578535e-05, "loss": 0.5847, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.4937251552185722, "learning_rate": 3.2488736568664756e-05, "loss": 0.53, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.5256657581320137, "learning_rate": 3.244451351193935e-05, "loss": 0.5863, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.5199720449340719, "learning_rate": 3.240019094921551e-05, "loss": 0.5374, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.5040816568397106, "learning_rate": 3.235576923489527e-05, "loss": 0.5465, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.5331344140694235, "learning_rate": 3.2311248724173476e-05, "loss": 0.5487, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5267197531249315, "learning_rate": 3.226662977303494e-05, "loss": 0.5193, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.5624283454120899, "learning_rate": 3.2221912738251626e-05, "loss": 0.5207, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.4591523275682814, "learning_rate": 3.2177097977379736e-05, "loss": 0.5081, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.5397384188680802, "learning_rate": 3.21321858487569e-05, "loss": 0.5232, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4834314479668938, "learning_rate": 3.208717671149931e-05, "loss": 0.5292, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.5420974817036738, "learning_rate": 3.204207092549882e-05, "loss": 0.5469, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.48113736231553167, "learning_rate": 3.19968688514201e-05, "loss": 0.5421, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.6019446578544221, "learning_rate": 3.195157085069774e-05, "loss": 0.54, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.5240961653080023, "learning_rate": 3.190617728553332e-05, "loss": 0.5572, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.5425599002203456, "learning_rate": 3.1860688518892606e-05, "loss": 0.5044, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.5288875397857601, "learning_rate": 3.181510491450254e-05, "loss": 0.5394, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.47566781854767715, "learning_rate": 3.176942683684842e-05, "loss": 0.526, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.544758229694233, "learning_rate": 3.1723654651170934e-05, "loss": 0.5395, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4835989015608882, "learning_rate": 3.167778872346327e-05, "loss": 0.5066, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.500498568242607, "learning_rate": 3.163182942046815e-05, "loss": 0.5457, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.5185174668718702, "learning_rate": 3.158577710967494e-05, "loss": 0.5521, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.5138731972306027, "learning_rate": 3.153963215931669e-05, "loss": 0.5194, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.48819650825461175, "learning_rate": 3.14933949383672e-05, "loss": 0.5329, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.5683115405412239, "learning_rate": 3.144706581653805e-05, "loss": 0.5463, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.5278604748519328, "learning_rate": 3.140064516427566e-05, "loss": 0.5233, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.5784100316694522, "learning_rate": 3.135413335275833e-05, "loss": 0.5108, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.5602883796298521, "learning_rate": 3.130753075389327e-05, "loss": 0.5482, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.5626965105274011, "learning_rate": 3.1260837740313625e-05, "loss": 0.5274, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.5165354879867671, "learning_rate": 3.121405468537547e-05, "loss": 0.5405, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.5105829232577068, "learning_rate": 3.116718196315488e-05, "loss": 0.5153, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.5433768296582815, "learning_rate": 3.1120219948444894e-05, "loss": 0.5436, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.5206228491716282, "learning_rate": 3.107316901675252e-05, "loss": 0.53, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.6208868604653215, "learning_rate": 3.1026029544295745e-05, "loss": 0.5643, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.488112129759074, "learning_rate": 3.097880190800057e-05, "loss": 0.5354, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.5853867626099835, "learning_rate": 3.093148648549788e-05, "loss": 0.5507, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4943495939639678, "learning_rate": 3.088408365512055e-05, "loss": 0.5524, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.513077472381657, "learning_rate": 3.083659379590034e-05, "loss": 0.5339, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.5547609914057182, "learning_rate": 3.0789017287564913e-05, "loss": 0.5469, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.48469704627216953, "learning_rate": 3.074135451053475e-05, "loss": 0.5216, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.6053863953943215, "learning_rate": 3.069360584592015e-05, "loss": 0.5536, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.5322724506553806, "learning_rate": 3.064577167551816e-05, "loss": 0.5312, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.5240118246862892, "learning_rate": 3.059785238180953e-05, "loss": 0.5246, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.5154276567758295, "learning_rate": 3.054984834795566e-05, "loss": 0.513, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.4930293851758491, "learning_rate": 3.0501759957795537e-05, "loss": 0.5209, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.4953332984886033, "learning_rate": 3.0453587595842627e-05, "loss": 0.5202, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4796823411471103, "learning_rate": 3.0405331647281856e-05, "loss": 0.5176, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.49823175680440507, "learning_rate": 3.0356992497966508e-05, "loss": 0.5232, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.5007637159863618, "learning_rate": 3.0308570534415137e-05, "loss": 0.5265, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.5427156282094961, "learning_rate": 3.0260066143808467e-05, "loss": 0.5412, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.4843102829512727, "learning_rate": 3.021147971398632e-05, "loss": 0.5288, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.5160601699416295, "learning_rate": 3.0162811633444478e-05, "loss": 0.5291, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.4541113355411976, "learning_rate": 3.0114062291331635e-05, "loss": 0.5398, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.5200584403048542, "learning_rate": 3.0065232077446217e-05, "loss": 0.5318, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.4863917007524842, "learning_rate": 3.001632138223332e-05, "loss": 0.5344, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.8662872389556419, "learning_rate": 2.9967330596781565e-05, "loss": 0.3678, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.8012996339257382, "learning_rate": 2.9918260112819952e-05, "loss": 0.3697, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.8853253354149592, "learning_rate": 2.9869110322714778e-05, "loss": 0.3623, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.6256673425384225, "learning_rate": 2.9819881619466447e-05, "loss": 0.3539, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.6724758434455853, "learning_rate": 2.9770574396706364e-05, "loss": 0.355, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5570785874945161, "learning_rate": 2.972118904869376e-05, "loss": 0.3697, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.6050252757923972, "learning_rate": 2.9671725970312563e-05, "loss": 0.3634, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5527383662348888, "learning_rate": 2.9622185557068238e-05, "loss": 0.3569, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.6172919934567423, "learning_rate": 2.95725682050846e-05, "loss": 0.35, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.5152766180544401, "learning_rate": 2.9522874311100684e-05, "loss": 0.3456, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.5774875682771987, "learning_rate": 2.9473104272467526e-05, "loss": 0.3454, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.5289567281505113, "learning_rate": 2.942325848714505e-05, "loss": 0.3635, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.5201554540729677, "learning_rate": 2.9373337353698804e-05, "loss": 0.3566, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4886563000579682, "learning_rate": 2.932334127129686e-05, "loss": 0.3775, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.5338319297104261, "learning_rate": 2.9273270639706547e-05, "loss": 0.3518, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.48725199577444367, "learning_rate": 2.922312585929131e-05, "loss": 0.3516, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.5598122773217423, "learning_rate": 2.9172907331007478e-05, "loss": 0.3771, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.5131827596497214, "learning_rate": 2.9122615456401053e-05, "loss": 0.3665, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.5053547475304238, "learning_rate": 2.9072250637604535e-05, "loss": 0.3626, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 1.8446253332640807, "learning_rate": 2.9021813277333667e-05, "loss": 0.3485, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.5441260367117259, "learning_rate": 2.8971303778884244e-05, "loss": 0.3657, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.5049029200052345, "learning_rate": 2.8920722546128863e-05, "loss": 0.3521, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.46868869698362814, "learning_rate": 2.887006998351372e-05, "loss": 0.3775, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.49349104224882134, "learning_rate": 2.881934649605535e-05, "loss": 0.3613, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.5315504206487948, "learning_rate": 2.8768552489337408e-05, "loss": 0.3474, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.5951988015517857, "learning_rate": 2.8717688369507425e-05, "loss": 0.3326, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.511585506590779, "learning_rate": 2.8666754543273535e-05, "loss": 0.3653, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4920268933454637, "learning_rate": 2.8615751417901273e-05, "loss": 0.3394, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.46999100777163444, "learning_rate": 2.856467940121025e-05, "loss": 0.3719, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.48961674837005786, "learning_rate": 2.8513538901570964e-05, "loss": 0.3625, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.5225585820428801, "learning_rate": 2.846233032790149e-05, "loss": 0.3564, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.47263089957693283, "learning_rate": 2.84110540896642e-05, "loss": 0.3718, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.48765148566231553, "learning_rate": 2.8359710596862555e-05, "loss": 0.3311, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.45345374451389614, "learning_rate": 2.8308300260037734e-05, "loss": 0.3414, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.5431075644710467, "learning_rate": 2.8256823490265424e-05, "loss": 0.3519, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.5376817703868266, "learning_rate": 2.8205280699152515e-05, "loss": 0.3869, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.55942344462929, "learning_rate": 2.8153672298833777e-05, "loss": 0.3728, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.5097657748387432, "learning_rate": 2.8101998701968615e-05, "loss": 0.3577, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.5066436429409239, "learning_rate": 2.805026032173773e-05, "loss": 0.3913, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.5298414674790121, "learning_rate": 2.7998457571839832e-05, "loss": 0.3522, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.5402979005122274, "learning_rate": 2.7946590866488322e-05, "loss": 0.3638, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.553417061160524, "learning_rate": 2.7894660620408e-05, "loss": 0.3698, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.49133529025892897, "learning_rate": 2.784266724883173e-05, "loss": 0.3592, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.5084201542776423, "learning_rate": 2.7790611167497128e-05, "loss": 0.3719, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.5283562970358473, "learning_rate": 2.7738492792643224e-05, "loss": 0.3651, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.489171979170402, "learning_rate": 2.768631254100716e-05, "loss": 0.3489, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.4872509353302852, "learning_rate": 2.7634070829820836e-05, "loss": 0.3569, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.5741541646444003, "learning_rate": 2.7581768076807592e-05, "loss": 0.3687, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.48912393984377733, "learning_rate": 2.7529404700178832e-05, "loss": 0.38, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.6182021639068218, "learning_rate": 2.7476981118630735e-05, "loss": 0.3583, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.5350957973429477, "learning_rate": 2.742449775134085e-05, "loss": 0.3591, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.48315058164038727, "learning_rate": 2.7371955017964788e-05, "loss": 0.3568, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.5384307184571415, "learning_rate": 2.7319353338632845e-05, "loss": 0.3424, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.5145265254665123, "learning_rate": 2.7266693133946645e-05, "loss": 0.3794, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.4602566261192792, "learning_rate": 2.7213974824975785e-05, "loss": 0.3616, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.4834860596865379, "learning_rate": 2.7161198833254464e-05, "loss": 0.3273, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.507502913353008, "learning_rate": 2.7108365580778095e-05, "loss": 0.3666, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.5125914143802089, "learning_rate": 2.705547548999996e-05, "loss": 0.3689, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.474071445116445, "learning_rate": 2.7002528983827817e-05, "loss": 0.3522, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.4803551553294673, "learning_rate": 2.6949526485620517e-05, "loss": 0.3695, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.49719231246374945, "learning_rate": 2.6896468419184623e-05, "loss": 0.3781, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.5256773214880658, "learning_rate": 2.6843355208771024e-05, "loss": 0.3408, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.46100301892223083, "learning_rate": 2.6790187279071536e-05, "loss": 0.3499, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.5152632456815294, "learning_rate": 2.67369650552155e-05, "loss": 0.3564, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.45855943025171525, "learning_rate": 2.6683688962766407e-05, "loss": 0.3572, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.5160006509772281, "learning_rate": 2.6630359427718468e-05, "loss": 0.3533, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.4570073631070164, "learning_rate": 2.6576976876493225e-05, "loss": 0.3376, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.4757993452570901, "learning_rate": 2.652354173593614e-05, "loss": 0.3681, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.4676157211705179, "learning_rate": 2.647005443331317e-05, "loss": 0.3769, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.4466569384328499, "learning_rate": 2.6416515396307354e-05, "loss": 0.3597, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.47598921020390583, "learning_rate": 2.636292505301542e-05, "loss": 0.388, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.45914773217982957, "learning_rate": 2.630928383194431e-05, "loss": 0.3444, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.479422716341347, "learning_rate": 2.625559216200781e-05, "loss": 0.358, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5359118393716397, "learning_rate": 2.620185047252308e-05, "loss": 0.3551, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.4603250402512299, "learning_rate": 2.614805919320723e-05, "loss": 0.3645, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.5323911678899507, "learning_rate": 2.6094218754173895e-05, "loss": 0.3773, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.49989434981959185, "learning_rate": 2.60403295859298e-05, "loss": 0.3491, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.47927915902575663, "learning_rate": 2.5986392119371297e-05, "loss": 0.3548, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.5101988422952396, "learning_rate": 2.5932406785780928e-05, "loss": 0.353, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.49008208295575806, "learning_rate": 2.5878374016823987e-05, "loss": 0.3599, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.48982964943533763, "learning_rate": 2.5824294244545045e-05, "loss": 0.3762, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.5039197042971496, "learning_rate": 2.577016790136453e-05, "loss": 0.353, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.5250944691203862, "learning_rate": 2.5715995420075225e-05, "loss": 0.3668, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.48458823112495863, "learning_rate": 2.5661777233838864e-05, "loss": 0.3631, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.4725049247987082, "learning_rate": 2.5607513776182616e-05, "loss": 0.3618, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.5195922585091483, "learning_rate": 2.5553205480995633e-05, "loss": 0.3718, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.4385444877058548, "learning_rate": 2.5498852782525604e-05, "loss": 0.3759, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.5050916312363531, "learning_rate": 2.5444456115375252e-05, "loss": 0.3684, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.47550885526858827, "learning_rate": 2.539001591449889e-05, "loss": 0.3666, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.44227968872154055, "learning_rate": 2.53355326151989e-05, "loss": 0.3606, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.4915870106275072, "learning_rate": 2.5281006653122288e-05, "loss": 0.3529, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.5142061897795196, "learning_rate": 2.5226438464257217e-05, "loss": 0.3586, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.472708893616078, "learning_rate": 2.5171828484929447e-05, "loss": 0.3749, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.4974623394590295, "learning_rate": 2.5117177151798934e-05, "loss": 0.3547, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.4536624602497348, "learning_rate": 2.506248490185627e-05, "loss": 0.3453, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.5203334752505799, "learning_rate": 2.500775217241923e-05, "loss": 0.3744, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4740648435783489, "learning_rate": 2.4952979401129266e-05, "loss": 0.367, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.4582831454768068, "learning_rate": 2.4898167025948e-05, "loss": 0.3675, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.4941445464720867, "learning_rate": 2.4843315485153703e-05, "loss": 0.3586, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.4762394529320864, "learning_rate": 2.4788425217337856e-05, "loss": 0.364, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.4954073678250344, "learning_rate": 2.4733496661401572e-05, "loss": 0.3719, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.47959854441842154, "learning_rate": 2.4678530256552114e-05, "loss": 0.3694, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.479712805997058, "learning_rate": 2.46235264422994e-05, "loss": 0.3667, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.4923183107077437, "learning_rate": 2.4568485658452452e-05, "loss": 0.379, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.5156550801501149, "learning_rate": 2.451340834511592e-05, "loss": 0.3793, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.47122615884645636, "learning_rate": 2.4458294942686528e-05, "loss": 0.3678, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.43682869938240887, "learning_rate": 2.440314589184958e-05, "loss": 0.3701, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.5056551391933813, "learning_rate": 2.434796163357541e-05, "loss": 0.3513, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.49762541960374623, "learning_rate": 2.429274260911588e-05, "loss": 0.3578, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.4711996566024965, "learning_rate": 2.423748926000084e-05, "loss": 0.3732, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.45468858260478245, "learning_rate": 2.418220202803459e-05, "loss": 0.3814, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.44935570326749663, "learning_rate": 2.412688135529237e-05, "loss": 0.3719, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.47626645746616864, "learning_rate": 2.4071527684116807e-05, "loss": 0.3681, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.45735641695699436, "learning_rate": 2.4016141457114372e-05, "loss": 0.3767, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.4826516121271409, "learning_rate": 2.396072311715187e-05, "loss": 0.3692, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.4850804113941549, "learning_rate": 2.3905273107352863e-05, "loss": 0.3857, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.4825324755082618, "learning_rate": 2.3849791871094157e-05, "loss": 0.3728, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.48418722824705157, "learning_rate": 2.379427985200223e-05, "loss": 0.359, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.4567065775657819, "learning_rate": 2.373873749394972e-05, "loss": 0.3745, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.49403421650090157, "learning_rate": 2.3683165241051836e-05, "loss": 0.3492, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.514957921590616, "learning_rate": 2.3627563537662823e-05, "loss": 0.3624, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.4656657931506011, "learning_rate": 2.3571932828372433e-05, "loss": 0.3808, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.46211138254363937, "learning_rate": 2.351627355800233e-05, "loss": 0.3657, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.49063960244304655, "learning_rate": 2.346058617160256e-05, "loss": 0.3658, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.4561569612067847, "learning_rate": 2.3404871114447976e-05, "loss": 0.3661, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.47177859545519996, "learning_rate": 2.334912883203469e-05, "loss": 0.374, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.44573276036289544, "learning_rate": 2.3293359770076505e-05, "loss": 0.3584, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.4424454281130908, "learning_rate": 2.323756437450136e-05, "loss": 0.3578, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.42926389428732664, "learning_rate": 2.3181743091447754e-05, "loss": 0.3654, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.4842627932482834, "learning_rate": 2.3125896367261164e-05, "loss": 0.3741, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.47278320813915126, "learning_rate": 2.307002464849052e-05, "loss": 0.3533, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.486205661500609, "learning_rate": 2.30141283818846e-05, "loss": 0.3806, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.45686372395224056, "learning_rate": 2.2958208014388462e-05, "loss": 0.3699, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.48964481181123337, "learning_rate": 2.2902263993139857e-05, "loss": 0.3817, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.46530494835924596, "learning_rate": 2.2846296765465708e-05, "loss": 0.3457, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.5137318721650532, "learning_rate": 2.2790306778878465e-05, "loss": 0.3877, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.43398248215416946, "learning_rate": 2.273429448107257e-05, "loss": 0.3414, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.4639385838411522, "learning_rate": 2.2678260319920868e-05, "loss": 0.3449, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.4960459708309143, "learning_rate": 2.262220474347102e-05, "loss": 0.3606, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.45987494222970926, "learning_rate": 2.2566128199941918e-05, "loss": 0.3703, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.48141763127465786, "learning_rate": 2.2510031137720104e-05, "loss": 0.3817, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.5160169748242509, "learning_rate": 2.2453914005356206e-05, "loss": 0.3651, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.4696065895024436, "learning_rate": 2.2397777251561302e-05, "loss": 0.3634, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.49214021310880884, "learning_rate": 2.2341621325203393e-05, "loss": 0.3813, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.46990564016725006, "learning_rate": 2.2285446675303764e-05, "loss": 0.35, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.49133822057457055, "learning_rate": 2.2229253751033423e-05, "loss": 0.3817, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.4936589440832987, "learning_rate": 2.2173043001709492e-05, "loss": 0.3894, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.4528322638090889, "learning_rate": 2.2116814876791627e-05, "loss": 0.3538, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.4443489855985849, "learning_rate": 2.2060569825878413e-05, "loss": 0.3611, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.4614872838936728, "learning_rate": 2.2004308298703777e-05, "loss": 0.3492, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.4582061914262008, "learning_rate": 2.1948030745133396e-05, "loss": 0.3516, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.4844337748770103, "learning_rate": 2.1891737615161083e-05, "loss": 0.3862, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.5029139217345048, "learning_rate": 2.1835429358905218e-05, "loss": 0.3639, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.46985825292732175, "learning_rate": 2.17791064266051e-05, "loss": 0.3569, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.4657023673637057, "learning_rate": 2.172276926861741e-05, "loss": 0.3579, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.45519917734092846, "learning_rate": 2.166641833541255e-05, "loss": 0.33, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.46263968195992267, "learning_rate": 2.161005407757109e-05, "loss": 0.3466, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.47188148246651235, "learning_rate": 2.155367694578013e-05, "loss": 0.3836, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.5126706388223633, "learning_rate": 2.1497287390829712e-05, "loss": 0.3574, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.4893190549854226, "learning_rate": 2.1440885863609208e-05, "loss": 0.3716, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.47278401695497035, "learning_rate": 2.1384472815103737e-05, "loss": 0.3533, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.5110686159083133, "learning_rate": 2.1328048696390534e-05, "loss": 0.3677, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.4760697657222583, "learning_rate": 2.1271613958635342e-05, "loss": 0.3691, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.482547700023665, "learning_rate": 2.1215169053088825e-05, "loss": 0.33, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.505413484372486, "learning_rate": 2.1158714431082937e-05, "loss": 0.3611, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.46205987294116263, "learning_rate": 2.110225054402733e-05, "loss": 0.3591, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.48280026617541955, "learning_rate": 2.1045777843405747e-05, "loss": 0.3384, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.5575342601190184, "learning_rate": 2.09892967807724e-05, "loss": 0.3698, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.48239952608326603, "learning_rate": 2.093280780774835e-05, "loss": 0.3408, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.5016480909491157, "learning_rate": 2.087631137601793e-05, "loss": 0.3511, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.4757404601627016, "learning_rate": 2.0819807937325104e-05, "loss": 0.3907, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.4492004066982867, "learning_rate": 2.0763297943469847e-05, "loss": 0.3605, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.5193076883800796, "learning_rate": 2.070678184630458e-05, "loss": 0.354, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.46257655540764575, "learning_rate": 2.06502600977305e-05, "loss": 0.3758, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.44189339058918414, "learning_rate": 2.0593733149694008e-05, "loss": 0.3634, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.45838842798607743, "learning_rate": 2.0537201454183074e-05, "loss": 0.3546, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.485667908659242, "learning_rate": 2.0480665463223626e-05, "loss": 0.3674, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.4404328869555377, "learning_rate": 2.042412562887594e-05, "loss": 0.356, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.43964958633601087, "learning_rate": 2.0367582403231033e-05, "loss": 0.3789, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.4514663473373361, "learning_rate": 2.0311036238407023e-05, "loss": 0.3761, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.45446316874799103, "learning_rate": 2.0254487586545534e-05, "loss": 0.3659, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.4450838892465161, "learning_rate": 2.0197936899808088e-05, "loss": 0.3392, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.49741533467289956, "learning_rate": 2.0141384630372466e-05, "loss": 0.3514, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.4568774465418769, "learning_rate": 2.0084831230429106e-05, "loss": 0.3608, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.4509772403333132, "learning_rate": 2.0028277152177492e-05, "loss": 0.3771, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.49033736061190053, "learning_rate": 1.9971722847822518e-05, "loss": 0.3859, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.4511213686153755, "learning_rate": 1.99151687695709e-05, "loss": 0.3324, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.44219496925916524, "learning_rate": 1.9858615369627537e-05, "loss": 0.337, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.5077390042598533, "learning_rate": 1.9802063100191916e-05, "loss": 0.3844, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.4512693347608976, "learning_rate": 1.974551241345447e-05, "loss": 0.3624, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.4680893101222838, "learning_rate": 1.9688963761592984e-05, "loss": 0.3553, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.4848645970738471, "learning_rate": 1.963241759676897e-05, "loss": 0.3518, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.44565356867270256, "learning_rate": 1.9575874371124066e-05, "loss": 0.356, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.46871335460499797, "learning_rate": 1.951933453677638e-05, "loss": 0.3553, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.464752971285992, "learning_rate": 1.9462798545816932e-05, "loss": 0.3562, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.4643167180353157, "learning_rate": 1.9406266850305996e-05, "loss": 0.3451, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.48164787510051377, "learning_rate": 1.9349739902269503e-05, "loss": 0.366, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.46896878121190505, "learning_rate": 1.9293218153695425e-05, "loss": 0.3347, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.45634887115689937, "learning_rate": 1.9236702056530153e-05, "loss": 0.3608, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.4308641289935243, "learning_rate": 1.9180192062674907e-05, "loss": 0.3548, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.4928719746761127, "learning_rate": 1.9123688623982076e-05, "loss": 0.3425, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.4668976228399319, "learning_rate": 1.906719219225165e-05, "loss": 0.3736, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.45466808665131714, "learning_rate": 1.9010703219227603e-05, "loss": 0.3793, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.42741757748459674, "learning_rate": 1.8954222156594256e-05, "loss": 0.3798, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.4858715422566963, "learning_rate": 1.8897749455972673e-05, "loss": 0.3666, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.4454193494640449, "learning_rate": 1.884128556891707e-05, "loss": 0.3561, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.496895604651705, "learning_rate": 1.878483094691119e-05, "loss": 0.3727, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.4730797448961459, "learning_rate": 1.8728386041364664e-05, "loss": 0.3906, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.441216981628127, "learning_rate": 1.867195130360947e-05, "loss": 0.3591, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.5012190135575463, "learning_rate": 1.8615527184896263e-05, "loss": 0.3825, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.47245351340632674, "learning_rate": 1.8559114136390795e-05, "loss": 0.3718, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.5020123260739213, "learning_rate": 1.8502712609170298e-05, "loss": 0.358, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.4445739436984716, "learning_rate": 1.8446323054219876e-05, "loss": 0.3368, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.5136334527475445, "learning_rate": 1.838994592242891e-05, "loss": 0.3603, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.44515232007534333, "learning_rate": 1.8333581664587453e-05, "loss": 0.3455, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.46574827690551707, "learning_rate": 1.8277230731382593e-05, "loss": 0.3539, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.4913942061808019, "learning_rate": 1.82208935733949e-05, "loss": 0.3887, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.45232308885752304, "learning_rate": 1.8164570641094793e-05, "loss": 0.3696, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.4261551957764673, "learning_rate": 1.810826238483892e-05, "loss": 0.3666, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.4426089740175935, "learning_rate": 1.8051969254866608e-05, "loss": 0.3564, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.4433573809082118, "learning_rate": 1.7995691701296226e-05, "loss": 0.3377, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.46570913763261035, "learning_rate": 1.7939430174121593e-05, "loss": 0.3726, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.4602827982806637, "learning_rate": 1.788318512320838e-05, "loss": 0.3858, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.4789223506940574, "learning_rate": 1.782695699829051e-05, "loss": 0.3711, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.4343065271988373, "learning_rate": 1.7770746248966587e-05, "loss": 0.3609, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.4389970003488385, "learning_rate": 1.7714553324696243e-05, "loss": 0.3737, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.46352089323817003, "learning_rate": 1.7658378674796614e-05, "loss": 0.3725, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.46867422474604553, "learning_rate": 1.76022227484387e-05, "loss": 0.371, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.41502711375870904, "learning_rate": 1.7546085994643807e-05, "loss": 0.3464, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.4488084631178499, "learning_rate": 1.7489968862279902e-05, "loss": 0.3671, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.41537714513936946, "learning_rate": 1.743387180005809e-05, "loss": 0.3675, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.4689674045604057, "learning_rate": 1.737779525652899e-05, "loss": 0.3592, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.43134479144239235, "learning_rate": 1.732173968007914e-05, "loss": 0.3664, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.48997148090784287, "learning_rate": 1.7265705518927437e-05, "loss": 0.3719, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.4612924932795784, "learning_rate": 1.7209693221121542e-05, "loss": 0.3424, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.45985470736189044, "learning_rate": 1.7153703234534302e-05, "loss": 0.3587, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.45967853043244356, "learning_rate": 1.709773600686015e-05, "loss": 0.3505, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.4612743688989382, "learning_rate": 1.7041791985611548e-05, "loss": 0.3626, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.42165298828957026, "learning_rate": 1.69858716181154e-05, "loss": 0.362, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.439736618597086, "learning_rate": 1.692997535150948e-05, "loss": 0.3642, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.45548578997901845, "learning_rate": 1.687410363273884e-05, "loss": 0.3488, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.4438862121939788, "learning_rate": 1.6818256908552257e-05, "loss": 0.3651, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3964903574892482, "learning_rate": 1.6762435625498646e-05, "loss": 0.3646, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.419388709635314, "learning_rate": 1.67066402299235e-05, "loss": 0.3315, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.4786861450356696, "learning_rate": 1.6650871167965313e-05, "loss": 0.3753, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.4424469499860328, "learning_rate": 1.6595128885552028e-05, "loss": 0.3516, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.42943568563180573, "learning_rate": 1.653941382839745e-05, "loss": 0.342, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.636014183313156, "learning_rate": 1.6483726441997673e-05, "loss": 0.2336, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.5118335495115021, "learning_rate": 1.642806717162757e-05, "loss": 0.2247, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.48296234808815464, "learning_rate": 1.637243646233718e-05, "loss": 0.2044, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.8227743302680887, "learning_rate": 1.6316834758948174e-05, "loss": 0.2054, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.6114705743718354, "learning_rate": 1.6261262506050282e-05, "loss": 0.211, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.45995967620168426, "learning_rate": 1.620572014799777e-05, "loss": 0.2199, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.56924466327057, "learning_rate": 1.6150208128905857e-05, "loss": 0.2145, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.5298985075036599, "learning_rate": 1.6094726892647147e-05, "loss": 0.2207, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.4828393382168547, "learning_rate": 1.6039276882848135e-05, "loss": 0.2225, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.4435713373443935, "learning_rate": 1.5983858542885635e-05, "loss": 0.2204, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.5072420612808682, "learning_rate": 1.5928472315883203e-05, "loss": 0.2152, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.5029171568218304, "learning_rate": 1.5873118644707633e-05, "loss": 0.2162, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.5134177561373612, "learning_rate": 1.5817797971965413e-05, "loss": 0.2337, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.45700616689898926, "learning_rate": 1.576251073999917e-05, "loss": 0.224, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.4345595681046122, "learning_rate": 1.5707257390884126e-05, "loss": 0.2163, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.476615769243583, "learning_rate": 1.5652038366424595e-05, "loss": 0.223, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.45506663939483016, "learning_rate": 1.5596854108150424e-05, "loss": 0.232, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.4326611244228883, "learning_rate": 1.5541705057313476e-05, "loss": 0.2109, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.43892547919412467, "learning_rate": 1.5486591654884086e-05, "loss": 0.2071, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.4487173062636214, "learning_rate": 1.543151434154755e-05, "loss": 0.2085, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.45840578894333756, "learning_rate": 1.5376473557700615e-05, "loss": 0.213, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.4788803551219879, "learning_rate": 1.5321469743447893e-05, "loss": 0.2358, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.42259984076621715, "learning_rate": 1.5266503338598434e-05, "loss": 0.2099, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.45268169143289766, "learning_rate": 1.5211574782662149e-05, "loss": 0.2161, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.4262856913294092, "learning_rate": 1.5156684514846307e-05, "loss": 0.1991, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.410321913483503, "learning_rate": 1.5101832974052012e-05, "loss": 0.1999, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.4137553677034252, "learning_rate": 1.5047020598870737e-05, "loss": 0.2337, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.45568530617540404, "learning_rate": 1.4992247827580778e-05, "loss": 0.2229, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.45769430054930865, "learning_rate": 1.493751509814374e-05, "loss": 0.2102, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.44323121453614306, "learning_rate": 1.4882822848201073e-05, "loss": 0.2051, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.4580928438745396, "learning_rate": 1.4828171515070553e-05, "loss": 0.2053, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.4440477712150846, "learning_rate": 1.4773561535742793e-05, "loss": 0.2019, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.40630174607648606, "learning_rate": 1.4718993346877715e-05, "loss": 0.22, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.4267582432557544, "learning_rate": 1.466446738480111e-05, "loss": 0.2194, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.4209651656351149, "learning_rate": 1.460998408550112e-05, "loss": 0.1974, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.40044874008524917, "learning_rate": 1.4555543884624751e-05, "loss": 0.2182, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.4231218314271417, "learning_rate": 1.4501147217474402e-05, "loss": 0.194, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.4107549520278094, "learning_rate": 1.444679451900437e-05, "loss": 0.231, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.42903509134983037, "learning_rate": 1.4392486223817397e-05, "loss": 0.2163, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.40791965229159616, "learning_rate": 1.4338222766161143e-05, "loss": 0.2125, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.4107195988796022, "learning_rate": 1.4284004579924777e-05, "loss": 0.2158, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.41557367954841945, "learning_rate": 1.4229832098635479e-05, "loss": 0.2142, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.4149067941939086, "learning_rate": 1.4175705755454963e-05, "loss": 0.2197, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.3851773164432949, "learning_rate": 1.412162598317602e-05, "loss": 0.2223, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.4145211739066912, "learning_rate": 1.406759321421907e-05, "loss": 0.1997, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.4125134220172743, "learning_rate": 1.401360788062871e-05, "loss": 0.2023, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.4050467181025358, "learning_rate": 1.3959670414070204e-05, "loss": 0.2271, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.4442208255153169, "learning_rate": 1.3905781245826108e-05, "loss": 0.2054, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.39914852660183625, "learning_rate": 1.3851940806792778e-05, "loss": 0.2031, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.42702630376293044, "learning_rate": 1.379814952747693e-05, "loss": 0.1972, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.4354850345268127, "learning_rate": 1.3744407837992193e-05, "loss": 0.1957, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.38884509909487047, "learning_rate": 1.3690716168055692e-05, "loss": 0.2037, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.40510255410754215, "learning_rate": 1.363707494698459e-05, "loss": 0.2141, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.4124152478769446, "learning_rate": 1.358348460369265e-05, "loss": 0.2295, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.4034540399190205, "learning_rate": 1.352994556668684e-05, "loss": 0.2063, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.4245537966947879, "learning_rate": 1.3476458264063865e-05, "loss": 0.2291, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.4062389498559749, "learning_rate": 1.342302312350678e-05, "loss": 0.2224, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.40388380791722917, "learning_rate": 1.3369640572281537e-05, "loss": 0.2125, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.4385775512743081, "learning_rate": 1.3316311037233596e-05, "loss": 0.2064, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.39738838838500523, "learning_rate": 1.326303494478451e-05, "loss": 0.2117, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.40148217799466057, "learning_rate": 1.3209812720928472e-05, "loss": 0.2138, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.4497924563545598, "learning_rate": 1.315664479122898e-05, "loss": 0.2131, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.4086525544452113, "learning_rate": 1.3103531580815378e-05, "loss": 0.21, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.4229845468797757, "learning_rate": 1.3050473514379488e-05, "loss": 0.2022, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.4154487906789833, "learning_rate": 1.2997471016172188e-05, "loss": 0.2015, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.4118846509010944, "learning_rate": 1.2944524510000042e-05, "loss": 0.208, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.437588081676693, "learning_rate": 1.2891634419221908e-05, "loss": 0.2166, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.3862458250559892, "learning_rate": 1.2838801166745545e-05, "loss": 0.2188, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.41804540368538157, "learning_rate": 1.2786025175024216e-05, "loss": 0.1966, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.4200747414709924, "learning_rate": 1.2733306866053357e-05, "loss": 0.203, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.42986137429599414, "learning_rate": 1.2680646661367163e-05, "loss": 0.219, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.41959059162680984, "learning_rate": 1.2628044982035219e-05, "loss": 0.2145, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.4057355738280588, "learning_rate": 1.2575502248659155e-05, "loss": 0.222, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.4160457171474736, "learning_rate": 1.2523018881369269e-05, "loss": 0.2337, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.43746514731485875, "learning_rate": 1.2470595299821176e-05, "loss": 0.2117, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.404566151460069, "learning_rate": 1.2418231923192416e-05, "loss": 0.2307, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.42660591661975267, "learning_rate": 1.2365929170179165e-05, "loss": 0.1889, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.43876887315812485, "learning_rate": 1.2313687458992848e-05, "loss": 0.2109, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.39424455607815395, "learning_rate": 1.2261507207356785e-05, "loss": 0.2036, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.38276320317163776, "learning_rate": 1.220938883250288e-05, "loss": 0.2143, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.38400217128054165, "learning_rate": 1.215733275116827e-05, "loss": 0.2106, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.4243030943400556, "learning_rate": 1.2105339379592005e-05, "loss": 0.23, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.3938927817165918, "learning_rate": 1.2053409133511681e-05, "loss": 0.21, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.4032122633193814, "learning_rate": 1.2001542428160173e-05, "loss": 0.2273, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.42051522460892793, "learning_rate": 1.1949739678262278e-05, "loss": 0.2249, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.40125453277462136, "learning_rate": 1.189800129803139e-05, "loss": 0.2148, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.41052401757664514, "learning_rate": 1.1846327701166228e-05, "loss": 0.2106, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.42646599946125635, "learning_rate": 1.1794719300847493e-05, "loss": 0.1875, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.4199699265410837, "learning_rate": 1.1743176509734582e-05, "loss": 0.2132, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.41658783146842054, "learning_rate": 1.1691699739962275e-05, "loss": 0.206, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.40238457198093747, "learning_rate": 1.1640289403137456e-05, "loss": 0.2115, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.3995791270695697, "learning_rate": 1.1588945910335802e-05, "loss": 0.227, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.38123705192530194, "learning_rate": 1.1537669672098517e-05, "loss": 0.2369, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.37926200098315344, "learning_rate": 1.1486461098429036e-05, "loss": 0.2043, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.4042445548764063, "learning_rate": 1.1435320598789747e-05, "loss": 0.2248, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.41478217872606366, "learning_rate": 1.1384248582098736e-05, "loss": 0.2096, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.3963582069942277, "learning_rate": 1.1333245456726467e-05, "loss": 0.2282, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.3906239623749677, "learning_rate": 1.128231163049258e-05, "loss": 0.2009, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.3933749897741993, "learning_rate": 1.123144751066259e-05, "loss": 0.2116, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.40150023078970637, "learning_rate": 1.1180653503944657e-05, "loss": 0.2022, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.392697189522408, "learning_rate": 1.1129930016486287e-05, "loss": 0.2225, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.3947811213205037, "learning_rate": 1.107927745387114e-05, "loss": 0.2103, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.3857948097096566, "learning_rate": 1.1028696221115766e-05, "loss": 0.2178, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.3846040691088322, "learning_rate": 1.0978186722666341e-05, "loss": 0.2225, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.41020156142961395, "learning_rate": 1.0927749362395475e-05, "loss": 0.2168, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.42139091443394233, "learning_rate": 1.0877384543598954e-05, "loss": 0.2057, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.40051031044147267, "learning_rate": 1.0827092668992529e-05, "loss": 0.2255, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.39503726436598524, "learning_rate": 1.077687414070869e-05, "loss": 0.21, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.38507712044746606, "learning_rate": 1.0726729360293451e-05, "loss": 0.2226, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.41379042264643406, "learning_rate": 1.0676658728703147e-05, "loss": 0.2385, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.39945859711755904, "learning_rate": 1.0626662646301198e-05, "loss": 0.2121, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.38560597955916365, "learning_rate": 1.0576741512854958e-05, "loss": 0.1973, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.42571043172296696, "learning_rate": 1.052689572753247e-05, "loss": 0.2162, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.3917891118854372, "learning_rate": 1.0477125688899328e-05, "loss": 0.235, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.38690919256167805, "learning_rate": 1.0427431794915406e-05, "loss": 0.2005, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.3998424462672751, "learning_rate": 1.0377814442931769e-05, "loss": 0.2197, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.4125542195833651, "learning_rate": 1.0328274029687439e-05, "loss": 0.2126, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.36955248438103355, "learning_rate": 1.0278810951306253e-05, "loss": 0.2342, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.4205881136167727, "learning_rate": 1.0229425603293647e-05, "loss": 0.2012, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.4077126438979775, "learning_rate": 1.0180118380533558e-05, "loss": 0.2108, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.4143490894616388, "learning_rate": 1.0130889677285225e-05, "loss": 0.2236, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.41140992539080645, "learning_rate": 1.008173988718005e-05, "loss": 0.2121, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.3867514364042829, "learning_rate": 1.0032669403218439e-05, "loss": 0.225, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.406569779418635, "learning_rate": 9.983678617766677e-06, "loss": 0.2474, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.3854547089372401, "learning_rate": 9.934767922553788e-06, "loss": 0.2078, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.3974987419731273, "learning_rate": 9.885937708668371e-06, "loss": 0.1972, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.3910607433193398, "learning_rate": 9.837188366555524e-06, "loss": 0.2068, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.4209225694472603, "learning_rate": 9.788520286013691e-06, "loss": 0.2053, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.4346227132639999, "learning_rate": 9.739933856191537e-06, "loss": 0.2166, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.37872977756465587, "learning_rate": 9.691429465584866e-06, "loss": 0.2134, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.4084288905083597, "learning_rate": 9.643007502033492e-06, "loss": 0.2128, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.4148947077560577, "learning_rate": 9.594668352718152e-06, "loss": 0.2203, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.36472616095191773, "learning_rate": 9.546412404157383e-06, "loss": 0.2104, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.39249953471530585, "learning_rate": 9.498240042204471e-06, "loss": 0.2058, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.4023609150846566, "learning_rate": 9.450151652044339e-06, "loss": 0.19, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.406399695823364, "learning_rate": 9.402147618190472e-06, "loss": 0.2029, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.39392978737555545, "learning_rate": 9.354228324481841e-06, "loss": 0.2056, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.38941400879477595, "learning_rate": 9.306394154079852e-06, "loss": 0.185, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.4128124815618466, "learning_rate": 9.258645489465254e-06, "loss": 0.201, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.4275783654916102, "learning_rate": 9.21098271243509e-06, "loss": 0.2254, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.40361967768728185, "learning_rate": 9.163406204099659e-06, "loss": 0.2184, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.4099439227242094, "learning_rate": 9.115916344879452e-06, "loss": 0.2119, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.439616942220103, "learning_rate": 9.068513514502126e-06, "loss": 0.204, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.41046739397106774, "learning_rate": 9.021198091999439e-06, "loss": 0.2109, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.41773808900154963, "learning_rate": 8.973970455704251e-06, "loss": 0.1988, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.3935594691797344, "learning_rate": 8.926830983247495e-06, "loss": 0.2122, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.4516147587177518, "learning_rate": 8.879780051555116e-06, "loss": 0.2054, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.4062332968551783, "learning_rate": 8.83281803684512e-06, "loss": 0.2124, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.3830116117961058, "learning_rate": 8.785945314624532e-06, "loss": 0.2037, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.43120900566901166, "learning_rate": 8.739162259686385e-06, "loss": 0.2097, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.4186444996820161, "learning_rate": 8.692469246106734e-06, "loss": 0.2064, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.39395517059986096, "learning_rate": 8.645866647241677e-06, "loss": 0.1938, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.4021587692602549, "learning_rate": 8.599354835724348e-06, "loss": 0.2011, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.425774594343249, "learning_rate": 8.552934183461958e-06, "loss": 0.2224, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.4058609232489085, "learning_rate": 8.506605061632805e-06, "loss": 0.2282, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.4197016946746771, "learning_rate": 8.460367840683308e-06, "loss": 0.2185, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.3952539517520363, "learning_rate": 8.414222890325065e-06, "loss": 0.1989, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.42152907968439435, "learning_rate": 8.368170579531855e-06, "loss": 0.209, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.4031272031093481, "learning_rate": 8.322211276536733e-06, "loss": 0.2, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.40186619308759636, "learning_rate": 8.27634534882907e-06, "loss": 0.2086, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.4179178101710705, "learning_rate": 8.230573163151585e-06, "loss": 0.2211, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.40188803716024996, "learning_rate": 8.184895085497466e-06, "loss": 0.2077, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.3614242553852074, "learning_rate": 8.139311481107401e-06, "loss": 0.2044, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.3870267123291121, "learning_rate": 8.093822714466686e-06, "loss": 0.2067, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.40808281936151153, "learning_rate": 8.048429149302271e-06, "loss": 0.2483, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.40016677793278715, "learning_rate": 8.003131148579902e-06, "loss": 0.2198, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.40764018047914136, "learning_rate": 7.957929074501182e-06, "loss": 0.2288, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.41776527102742944, "learning_rate": 7.912823288500695e-06, "loss": 0.2095, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.39586475071623534, "learning_rate": 7.867814151243102e-06, "loss": 0.2321, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.40287817031432194, "learning_rate": 7.822902022620267e-06, "loss": 0.2156, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.39269877688922694, "learning_rate": 7.778087261748377e-06, "loss": 0.208, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.36656083545915225, "learning_rate": 7.733370226965056e-06, "loss": 0.2133, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.36841232563864973, "learning_rate": 7.688751275826527e-06, "loss": 0.1928, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.3992783115170812, "learning_rate": 7.644230765104735e-06, "loss": 0.2364, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.4115171242539081, "learning_rate": 7.599809050784502e-06, "loss": 0.2211, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.38594205447248103, "learning_rate": 7.555486488060661e-06, "loss": 0.2208, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.39534870843070624, "learning_rate": 7.511263431335249e-06, "loss": 0.1883, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.38371768670295153, "learning_rate": 7.467140234214656e-06, "loss": 0.2036, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.3719807405677326, "learning_rate": 7.423117249506777e-06, "loss": 0.2131, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.3793866139620921, "learning_rate": 7.379194829218231e-06, "loss": 0.1932, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.3893366589375326, "learning_rate": 7.335373324551518e-06, "loss": 0.1992, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.38286033573811684, "learning_rate": 7.291653085902224e-06, "loss": 0.2153, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.41360238001204885, "learning_rate": 7.248034462856213e-06, "loss": 0.2094, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.3956328848460286, "learning_rate": 7.20451780418683e-06, "loss": 0.2102, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.37933937791393363, "learning_rate": 7.161103457852128e-06, "loss": 0.2199, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.3848387291085976, "learning_rate": 7.117791770992046e-06, "loss": 0.2185, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.36608628143233607, "learning_rate": 7.074583089925688e-06, "loss": 0.2128, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.3957101454389367, "learning_rate": 7.0314777601485155e-06, "loss": 0.2156, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.3971130262668965, "learning_rate": 6.988476126329604e-06, "loss": 0.1946, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.38150799292179677, "learning_rate": 6.945578532308857e-06, "loss": 0.2012, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.373321286967813, "learning_rate": 6.902785321094301e-06, "loss": 0.2076, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.38846008640486546, "learning_rate": 6.8600968348593115e-06, "loss": 0.2117, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.3754897951828383, "learning_rate": 6.817513414939892e-06, "loss": 0.2185, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.39739821179997276, "learning_rate": 6.775035401831924e-06, "loss": 0.2175, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.3853753506356513, "learning_rate": 6.732663135188473e-06, "loss": 0.1961, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.37882121506029415, "learning_rate": 6.690396953817055e-06, "loss": 0.2085, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.3980359955429777, "learning_rate": 6.648237195676927e-06, "loss": 0.2019, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.36662572706144336, "learning_rate": 6.606184197876395e-06, "loss": 0.2145, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.3807414006237544, "learning_rate": 6.564238296670109e-06, "loss": 0.2312, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.39085034883587516, "learning_rate": 6.52239982745638e-06, "loss": 0.2164, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.4066253501349732, "learning_rate": 6.480669124774484e-06, "loss": 0.1842, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.4086471984400369, "learning_rate": 6.439046522302013e-06, "loss": 0.1969, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.4001573392259027, "learning_rate": 6.397532352852191e-06, "loss": 0.2113, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.3741930657072497, "learning_rate": 6.356126948371202e-06, "loss": 0.2095, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.4070141392261277, "learning_rate": 6.314830639935559e-06, "loss": 0.2158, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.3992826300670988, "learning_rate": 6.273643757749448e-06, "loss": 0.2175, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.4021116536812563, "learning_rate": 6.2325666311420856e-06, "loss": 0.1944, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.3723112605800616, "learning_rate": 6.1915995885650675e-06, "loss": 0.2044, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.40929520763513794, "learning_rate": 6.150742957589784e-06, "loss": 0.1965, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.3744040658972661, "learning_rate": 6.109997064904774e-06, "loss": 0.2152, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.40190939107189044, "learning_rate": 6.069362236313092e-06, "loss": 0.2133, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.38783829511626833, "learning_rate": 6.0288387967297565e-06, "loss": 0.2099, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.3839377258178583, "learning_rate": 5.988427070179108e-06, "loss": 0.2123, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.3845030684322412, "learning_rate": 5.948127379792234e-06, "loss": 0.1887, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.4139338061078642, "learning_rate": 5.90794004780439e-06, "loss": 0.2045, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.3928095084268692, "learning_rate": 5.867865395552405e-06, "loss": 0.2313, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.3728958070813616, "learning_rate": 5.8279037434721364e-06, "loss": 0.2031, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.4021041455627079, "learning_rate": 5.788055411095892e-06, "loss": 0.2171, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.3811150444300799, "learning_rate": 5.7483207170498625e-06, "loss": 0.1993, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.38050322085042493, "learning_rate": 5.708699979051613e-06, "loss": 0.2061, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.3658195235951011, "learning_rate": 5.66919351390751e-06, "loss": 0.2056, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.36653765050926784, "learning_rate": 5.629801637510188e-06, "loss": 0.2121, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.37655474036256387, "learning_rate": 5.590524664836043e-06, "loss": 0.204, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.3841572156884536, "learning_rate": 5.551362909942708e-06, "loss": 0.1891, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.38806863094680955, "learning_rate": 5.51231668596653e-06, "loss": 0.2209, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.37857512641515056, "learning_rate": 5.47338630512007e-06, "loss": 0.1891, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.38294580461832123, "learning_rate": 5.434572078689617e-06, "loss": 0.1957, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.3929161573815731, "learning_rate": 5.395874317032694e-06, "loss": 0.2108, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.3726277175116964, "learning_rate": 5.357293329575573e-06, "loss": 0.2039, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.3688019144350598, "learning_rate": 5.318829424810797e-06, "loss": 0.2216, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.4016527126840202, "learning_rate": 5.280482910294728e-06, "loss": 0.2283, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.39663170068598075, "learning_rate": 5.242254092645078e-06, "loss": 0.2072, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.37429858351753903, "learning_rate": 5.2041432775384445e-06, "loss": 0.2036, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.3792446425015193, "learning_rate": 5.166150769707892e-06, "loss": 0.2383, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.3880098877120608, "learning_rate": 5.128276872940503e-06, "loss": 0.2056, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.38135895081829546, "learning_rate": 5.090521890074953e-06, "loss": 0.2034, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.4351647629392015, "learning_rate": 5.0528861229990675e-06, "loss": 0.1973, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.3813309013411489, "learning_rate": 5.015369872647442e-06, "loss": 0.2124, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.3893268779899761, "learning_rate": 4.9779734389990195e-06, "loss": 0.1928, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.38325612655860214, "learning_rate": 4.940697121074675e-06, "loss": 0.2335, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.39293458238647483, "learning_rate": 4.903541216934864e-06, "loss": 0.2066, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.3695873729869199, "learning_rate": 4.8665060236772e-06, "loss": 0.2422, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.4172256087821369, "learning_rate": 4.829591837434102e-06, "loss": 0.2142, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.37955638289653126, "learning_rate": 4.792798953370424e-06, "loss": 0.2059, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.37561217766226196, "learning_rate": 4.756127665681083e-06, "loss": 0.23, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.36007515352935315, "learning_rate": 4.719578267588725e-06, "loss": 0.2266, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.3933019493033677, "learning_rate": 4.6831510513413525e-06, "loss": 0.2002, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.5013541047781249, "learning_rate": 4.6468463082100176e-06, "loss": 0.1271, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.49047934101040686, "learning_rate": 4.610664328486485e-06, "loss": 0.1522, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.3803623247921018, "learning_rate": 4.5746054014809e-06, "loss": 0.1213, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.3344782553526108, "learning_rate": 4.5386698155194766e-06, "loss": 0.1413, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3486196809771522, "learning_rate": 4.502857857942204e-06, "loss": 0.1285, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.43610934174441407, "learning_rate": 4.467169815100549e-06, "loss": 0.1395, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.4723544361252343, "learning_rate": 4.431605972355137e-06, "loss": 0.1212, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.5092709641056857, "learning_rate": 4.396166614073516e-06, "loss": 0.1479, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.4412384289955588, "learning_rate": 4.360852023627846e-06, "loss": 0.1399, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3667749682961932, "learning_rate": 4.325662483392656e-06, "loss": 0.1229, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.3817226083415444, "learning_rate": 4.29059827474257e-06, "loss": 0.1414, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.37151082522289386, "learning_rate": 4.255659678050063e-06, "loss": 0.1164, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.3769319553748441, "learning_rate": 4.22084697268323e-06, "loss": 0.1321, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.41916687061636343, "learning_rate": 4.186160437003535e-06, "loss": 0.1573, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.38898029428995595, "learning_rate": 4.151600348363582e-06, "loss": 0.1365, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.3523533237439372, "learning_rate": 4.11716698310493e-06, "loss": 0.1331, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.3415212822419031, "learning_rate": 4.082860616555848e-06, "loss": 0.131, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.32843109721535946, "learning_rate": 4.048681523029125e-06, "loss": 0.1464, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.3420049199843974, "learning_rate": 4.014629975819882e-06, "loss": 0.1272, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.37187403715578965, "learning_rate": 3.9807062472033855e-06, "loss": 0.1327, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.37483845122656617, "learning_rate": 3.94691060843287e-06, "loss": 0.1332, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.38059290071238144, "learning_rate": 3.913243329737353e-06, "loss": 0.1261, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.34442358239950077, "learning_rate": 3.879704680319503e-06, "loss": 0.1032, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.33761678125921085, "learning_rate": 3.846294928353471e-06, "loss": 0.1191, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.34357465350821526, "learning_rate": 3.8130143409827345e-06, "loss": 0.1219, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.33817453793487334, "learning_rate": 3.7798631843179887e-06, "loss": 0.1411, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.31694870930365304, "learning_rate": 3.7468417234349973e-06, "loss": 0.1395, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.33462079914853654, "learning_rate": 3.7139502223724823e-06, "loss": 0.1477, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.34283722167692027, "learning_rate": 3.6811889441300095e-06, "loss": 0.139, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.3323126952909447, "learning_rate": 3.648558150665886e-06, "loss": 0.1385, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.3181277444855744, "learning_rate": 3.616058102895075e-06, "loss": 0.1321, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.3455422284521545, "learning_rate": 3.583689060687079e-06, "loss": 0.1344, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.34617723273599044, "learning_rate": 3.5514512828639023e-06, "loss": 0.1303, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.3447298438057964, "learning_rate": 3.51934502719796e-06, "loss": 0.1111, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.34539175921383675, "learning_rate": 3.4873705504100185e-06, "loss": 0.1509, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.33467966681886824, "learning_rate": 3.4555281081671345e-06, "loss": 0.1437, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.32766091060458846, "learning_rate": 3.4238179550806326e-06, "loss": 0.1381, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.3393810374634158, "learning_rate": 3.3922403447040497e-06, "loss": 0.1259, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.335541487962952, "learning_rate": 3.3607955295311247e-06, "loss": 0.1311, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.31901225167583447, "learning_rate": 3.32948376099375e-06, "loss": 0.1265, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.3368296435118173, "learning_rate": 3.2983052894599976e-06, "loss": 0.1112, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.33764570785859027, "learning_rate": 3.2672603642320945e-06, "loss": 0.1463, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.3513127776168016, "learning_rate": 3.236349233544438e-06, "loss": 0.1314, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.3296372050588214, "learning_rate": 3.205572144561604e-06, "loss": 0.1227, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.330760804336937, "learning_rate": 3.174929343376374e-06, "loss": 0.1242, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.3291816109890618, "learning_rate": 3.1444210750077777e-06, "loss": 0.1325, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.32376275799470366, "learning_rate": 3.1140475833991046e-06, "loss": 0.1176, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.32635350023241927, "learning_rate": 3.0838091114159895e-06, "loss": 0.1129, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.3107390104396183, "learning_rate": 3.0537059008444524e-06, "loss": 0.1085, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.3401091089047194, "learning_rate": 3.0237381923889563e-06, "loss": 0.1467, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.338711074009301, "learning_rate": 2.9939062256704997e-06, "loss": 0.125, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.34502073048556964, "learning_rate": 2.964210239224696e-06, "loss": 0.1298, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.3208657842800009, "learning_rate": 2.934650470499869e-06, "loss": 0.1476, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.32213205084540314, "learning_rate": 2.905227155855128e-06, "loss": 0.132, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.3454822627886586, "learning_rate": 2.875940530558519e-06, "loss": 0.1203, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.33856538625032717, "learning_rate": 2.8467908287851154e-06, "loss": 0.1246, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.3249906095235038, "learning_rate": 2.8177782836151603e-06, "loss": 0.1271, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.32125334807987865, "learning_rate": 2.7889031270321874e-06, "loss": 0.1208, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.3342652031000822, "learning_rate": 2.760165589921184e-06, "loss": 0.1245, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.3361589675962975, "learning_rate": 2.7315659020667305e-06, "loss": 0.1362, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.33786840969680587, "learning_rate": 2.703104292151164e-06, "loss": 0.1259, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.32711367241401573, "learning_rate": 2.6747809877527607e-06, "loss": 0.1165, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.34021291422991795, "learning_rate": 2.6465962153439082e-06, "loss": 0.1347, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.32168574536084893, "learning_rate": 2.618550200289303e-06, "loss": 0.1003, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.32554001399981297, "learning_rate": 2.59064316684412e-06, "loss": 0.1206, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.3079068501747365, "learning_rate": 2.562875338152264e-06, "loss": 0.138, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.32680688288924375, "learning_rate": 2.5352469362445552e-06, "loss": 0.1317, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.32208634184945845, "learning_rate": 2.5077581820369523e-06, "loss": 0.1361, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.3280577892880369, "learning_rate": 2.480409295328803e-06, "loss": 0.1358, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.3590949646914022, "learning_rate": 2.45320049480108e-06, "loss": 0.115, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.32356879995835786, "learning_rate": 2.4261319980146293e-06, "loss": 0.1295, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.32926667514178865, "learning_rate": 2.399204021408421e-06, "loss": 0.1186, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.3208575340978408, "learning_rate": 2.3724167802978395e-06, "loss": 0.1358, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.33221451480505465, "learning_rate": 2.3457704888729625e-06, "loss": 0.1332, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.3301478557254847, "learning_rate": 2.3192653601968162e-06, "loss": 0.1292, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.3222825103719906, "learning_rate": 2.2929016062037057e-06, "loss": 0.129, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.3329814458434315, "learning_rate": 2.2666794376975055e-06, "loss": 0.1286, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.32293028321616357, "learning_rate": 2.24059906434998e-06, "loss": 0.1138, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.3237927949322737, "learning_rate": 2.214660694699091e-06, "loss": 0.125, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.3278830665496914, "learning_rate": 2.188864536147355e-06, "loss": 0.1353, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.35408856354840823, "learning_rate": 2.1632107949601757e-06, "loss": 0.1347, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.32777379722105854, "learning_rate": 2.137699676264171e-06, "loss": 0.1226, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.310785500851812, "learning_rate": 2.1123313840455738e-06, "loss": 0.1211, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.32910466194169247, "learning_rate": 2.08710612114857e-06, "loss": 0.1284, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.3193703104801852, "learning_rate": 2.0620240892736953e-06, "loss": 0.1341, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.3248909024816723, "learning_rate": 2.0370854889762e-06, "loss": 0.1046, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.34294981559718146, "learning_rate": 2.0122905196644726e-06, "loss": 0.1394, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.33123336334852155, "learning_rate": 1.987639379598427e-06, "loss": 0.1225, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.3290593788419788, "learning_rate": 1.963132265887919e-06, "loss": 0.1156, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.32139087931199306, "learning_rate": 1.9387693744911784e-06, "loss": 0.1319, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.3495380336373183, "learning_rate": 1.9145509002132368e-06, "loss": 0.1217, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.31807368847083334, "learning_rate": 1.8904770367043723e-06, "loss": 0.1394, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.3285995995653189, "learning_rate": 1.8665479764585504e-06, "loss": 0.135, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.3172279784210053, "learning_rate": 1.8427639108118977e-06, "loss": 0.1247, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.30860174212012514, "learning_rate": 1.8191250299411755e-06, "loss": 0.1207, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.3250399704893487, "learning_rate": 1.7956315228622446e-06, "loss": 0.1138, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.3361586540004587, "learning_rate": 1.7722835774285553e-06, "loss": 0.1545, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.3327085837055863, "learning_rate": 1.7490813803296624e-06, "loss": 0.1285, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.3435536495718289, "learning_rate": 1.726025117089718e-06, "loss": 0.1204, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.3365667021384492, "learning_rate": 1.70311497206598e-06, "loss": 0.1146, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.32869782842825784, "learning_rate": 1.6803511284473638e-06, "loss": 0.1154, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.3216575753587075, "learning_rate": 1.6577337682529538e-06, "loss": 0.135, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.332967058791802, "learning_rate": 1.6352630723305617e-06, "loss": 0.1113, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.33117271186265523, "learning_rate": 1.612939220355272e-06, "loss": 0.127, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.331019031638403, "learning_rate": 1.5907623908280112e-06, "loss": 0.1396, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.3252309323798622, "learning_rate": 1.568732761074121e-06, "loss": 0.1172, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.32551807490523993, "learning_rate": 1.5468505072419237e-06, "loss": 0.1466, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.31332539277709404, "learning_rate": 1.5251158043013448e-06, "loss": 0.1399, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.31959729578275914, "learning_rate": 1.5035288260424885e-06, "loss": 0.1323, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.3345914879158336, "learning_rate": 1.4820897450742623e-06, "loss": 0.1297, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.3130871331777745, "learning_rate": 1.4607987328229767e-06, "loss": 0.1121, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.3365371817637923, "learning_rate": 1.4396559595310056e-06, "loss": 0.137, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.30824191739376483, "learning_rate": 1.4186615942553973e-06, "loss": 0.1327, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.3095884222336232, "learning_rate": 1.3978158048665424e-06, "loss": 0.129, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.32176510936205827, "learning_rate": 1.3771187580468115e-06, "loss": 0.145, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.3214356739937765, "learning_rate": 1.3565706192892392e-06, "loss": 0.1541, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.33941007244802207, "learning_rate": 1.3361715528961993e-06, "loss": 0.1224, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.3339637049079971, "learning_rate": 1.3159217219780817e-06, "loss": 0.1202, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.31886316252377606, "learning_rate": 1.2958212884519949e-06, "loss": 0.1203, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.33161052689696235, "learning_rate": 1.2758704130404675e-06, "loss": 0.109, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.3119113296984625, "learning_rate": 1.2560692552701738e-06, "loss": 0.1428, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.3421435556650435, "learning_rate": 1.2364179734706382e-06, "loss": 0.1226, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.3126271331219336, "learning_rate": 1.2169167247729852e-06, "loss": 0.1217, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.3255599894639427, "learning_rate": 1.1975656651086864e-06, "loss": 0.132, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.3441752110593626, "learning_rate": 1.1783649492082926e-06, "loss": 0.1278, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.32922545972057815, "learning_rate": 1.1593147306002183e-06, "loss": 0.1124, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.3393607121578277, "learning_rate": 1.140415161609505e-06, "loss": 0.1327, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.33278364215537093, "learning_rate": 1.121666393356604e-06, "loss": 0.1535, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.3431155153742259, "learning_rate": 1.1030685757561632e-06, "loss": 0.1342, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.30933272296638425, "learning_rate": 1.0846218575158373e-06, "loss": 0.1183, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.3341669106143087, "learning_rate": 1.066326386135097e-06, "loss": 0.1382, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.330768679915079, "learning_rate": 1.0481823079040398e-06, "loss": 0.1369, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.33030443348105615, "learning_rate": 1.0301897679022344e-06, "loss": 0.1196, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.31491110142417283, "learning_rate": 1.0123489099975491e-06, "loss": 0.1405, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.30747108109246074, "learning_rate": 9.9465987684501e-07, "loss": 0.1195, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.3188932716370111, "learning_rate": 9.771228098856534e-07, "loss": 0.1366, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.32330516085303984, "learning_rate": 9.597378493454013e-07, "loss": 0.141, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.33254120919388885, "learning_rate": 9.425051342339353e-07, "loss": 0.1552, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.3288468645166744, "learning_rate": 9.254248023435864e-07, "loss": 0.0977, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.3271387902942168, "learning_rate": 9.084969902482288e-07, "loss": 0.1294, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.34994252453163777, "learning_rate": 8.917218333021993e-07, "loss": 0.1142, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.3189857179219501, "learning_rate": 8.750994656392109e-07, "loss": 0.1396, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2983098931813602, "learning_rate": 8.58630020171265e-07, "loss": 0.1488, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.3539185937351737, "learning_rate": 8.423136285876099e-07, "loss": 0.131, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.32102465630940624, "learning_rate": 8.26150421353682e-07, "loss": 0.1115, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.3188902127153524, "learning_rate": 8.101405277100549e-07, "loss": 0.142, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.33063870072616947, "learning_rate": 7.942840756714077e-07, "loss": 0.1216, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.32979970431511435, "learning_rate": 7.785811920255093e-07, "loss": 0.1418, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.31731024911303984, "learning_rate": 7.630320023322024e-07, "loss": 0.1352, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.33322929404883506, "learning_rate": 7.476366309223903e-07, "loss": 0.1201, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.3295687978987999, "learning_rate": 7.323952008970537e-07, "loss": 0.1216, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.30623991966257336, "learning_rate": 7.173078341262618e-07, "loss": 0.123, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.31505341866851094, "learning_rate": 7.023746512481989e-07, "loss": 0.1404, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.3264551744986485, "learning_rate": 6.875957716681902e-07, "loss": 0.14, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.3239585421875172, "learning_rate": 6.729713135577687e-07, "loss": 0.1303, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.3263202056597652, "learning_rate": 6.585013938537143e-07, "loss": 0.1165, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.3372552797117872, "learning_rate": 6.441861282571115e-07, "loss": 0.1293, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.3294725540910654, "learning_rate": 6.300256312324471e-07, "loss": 0.1442, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.30835714872317355, "learning_rate": 6.160200160066776e-07, "loss": 0.1292, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.33464623837293084, "learning_rate": 6.021693945683327e-07, "loss": 0.1322, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.31672406695096794, "learning_rate": 5.884738776666044e-07, "loss": 0.1374, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.3180411756551934, "learning_rate": 5.749335748104878e-07, "loss": 0.1415, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.32863930271088954, "learning_rate": 5.615485942678778e-07, "loss": 0.1367, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.34820664161526294, "learning_rate": 5.483190430647289e-07, "loss": 0.1258, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.3290820483139421, "learning_rate": 5.352450269841747e-07, "loss": 0.132, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.3180248165604198, "learning_rate": 5.22326650565701e-07, "loss": 0.138, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.31474020009090714, "learning_rate": 5.095640171043048e-07, "loss": 0.1448, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.30535737871602137, "learning_rate": 4.969572286496594e-07, "loss": 0.1332, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.3131188492472144, "learning_rate": 4.845063860053079e-07, "loss": 0.1428, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.3205018094363858, "learning_rate": 4.7221158872785997e-07, "loss": 0.1167, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.32118022830242715, "learning_rate": 4.600729351261857e-07, "loss": 0.1169, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.3212158974004059, "learning_rate": 4.4809052226063355e-07, "loss": 0.124, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.34165330370041835, "learning_rate": 4.3626444594226046e-07, "loss": 0.1247, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2979776654123057, "learning_rate": 4.245948007320588e-07, "loss": 0.1223, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.31644823489045704, "learning_rate": 4.130816799401971e-07, "loss": 0.1328, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.3124667682103636, "learning_rate": 4.017251756252827e-07, "loss": 0.1486, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.3208891963195655, "learning_rate": 3.9052537859362473e-07, "loss": 0.1243, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.3275887367822634, "learning_rate": 3.7948237839849687e-07, "loss": 0.1225, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.3301388125325543, "learning_rate": 3.6859626333943797e-07, "loss": 0.1189, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.3188065135014096, "learning_rate": 3.578671204615347e-07, "loss": 0.1185, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.3456766061843505, "learning_rate": 3.472950355547267e-07, "loss": 0.117, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.3252369701889525, "learning_rate": 3.3688009315312244e-07, "loss": 0.1322, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.32034688665973876, "learning_rate": 3.266223765343224e-07, "loss": 0.1253, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.3339717580330911, "learning_rate": 3.16521967718757e-07, "loss": 0.15, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.3378358711187354, "learning_rate": 3.0657894746902726e-07, "loss": 0.1327, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.3345696631718408, "learning_rate": 2.9679339528925654e-07, "loss": 0.1356, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.33630489133674807, "learning_rate": 2.871653894244597e-07, "loss": 0.1212, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.33123384716217696, "learning_rate": 2.7769500685991266e-07, "loss": 0.14, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.3340778879953979, "learning_rate": 2.683823233205485e-07, "loss": 0.1219, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.3149221934720894, "learning_rate": 2.592274132703287e-07, "loss": 0.1225, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.34248217408587267, "learning_rate": 2.502303499116754e-07, "loss": 0.1499, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.3472062464153022, "learning_rate": 2.413912051848666e-07, "loss": 0.1121, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.33556772531303464, "learning_rate": 2.3271004976746613e-07, "loss": 0.1204, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.3133026777448893, "learning_rate": 2.2418695307376393e-07, "loss": 0.1403, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.3124186484291164, "learning_rate": 2.1582198325420968e-07, "loss": 0.1481, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.3228819455165503, "learning_rate": 2.0761520719488447e-07, "loss": 0.1228, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.32190078366389674, "learning_rate": 1.9956669051694798e-07, "loss": 0.1483, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.33579023746110126, "learning_rate": 1.916764975761254e-07, "loss": 0.1342, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.34213632882163875, "learning_rate": 1.839446914621923e-07, "loss": 0.137, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.3238368614240196, "learning_rate": 1.7637133399845962e-07, "loss": 0.1101, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.31588222067440785, "learning_rate": 1.6895648574129397e-07, "loss": 0.1305, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.3135714380955484, "learning_rate": 1.6170020597962465e-07, "loss": 0.1333, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.3123272140040331, "learning_rate": 1.5460255273447078e-07, "loss": 0.1277, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.30768871153183464, "learning_rate": 1.4766358275847715e-07, "loss": 0.1134, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.32532973153492023, "learning_rate": 1.4088335153546573e-07, "loss": 0.1325, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.33201309841057913, "learning_rate": 1.3426191327998496e-07, "loss": 0.1745, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.308779672212176, "learning_rate": 1.277993209368744e-07, "loss": 0.141, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.30897501259297155, "learning_rate": 1.214956261808542e-07, "loss": 0.1352, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.32158591276480336, "learning_rate": 1.1535087941609846e-07, "loss": 0.1135, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.3193434547263267, "learning_rate": 1.0936512977583802e-07, "loss": 0.118, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.3170916718552927, "learning_rate": 1.0353842512196732e-07, "loss": 0.1222, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.31685983704594717, "learning_rate": 9.787081204466253e-08, "loss": 0.1315, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.3184614469923699, "learning_rate": 9.236233586200627e-08, "loss": 0.1139, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.3067634713568435, "learning_rate": 8.70130406196279e-08, "loss": 0.1337, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.3438411526412573, "learning_rate": 8.182296909035047e-08, "loss": 0.1224, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.30895428255603774, "learning_rate": 7.679216277384439e-08, "loss": 0.1306, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.33309307037145947, "learning_rate": 7.19206618963053e-08, "loss": 0.1241, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.33295564262836047, "learning_rate": 6.720850541012347e-08, "loss": 0.1114, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.32023820527667124, "learning_rate": 6.265573099357714e-08, "loss": 0.1055, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.31933970908057385, "learning_rate": 5.826237505053067e-08, "loss": 0.1116, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.3248643400426225, "learning_rate": 5.4028472710137e-08, "loss": 0.129, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.31140636084677437, "learning_rate": 4.9954057826571146e-08, "loss": 0.1304, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.321000341803058, "learning_rate": 4.6039162978743776e-08, "loss": 0.129, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.31022779077687135, "learning_rate": 4.228381947004812e-08, "loss": 0.1005, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.3204679852042637, "learning_rate": 3.868805732811343e-08, "loss": 0.1354, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.31641039449080954, "learning_rate": 3.525190530455636e-08, "loss": 0.1371, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.32488113144091274, "learning_rate": 3.197539087475887e-08, "loss": 0.1385, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.32090749137240937, "learning_rate": 2.8858540237641786e-08, "loss": 0.1361, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.33658447902748867, "learning_rate": 2.5901378315458247e-08, "loss": 0.1174, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.3213269750768548, "learning_rate": 2.3103928753598347e-08, "loss": 0.1251, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.3282887868977182, "learning_rate": 2.0466213920393718e-08, "loss": 0.127, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.3141404212302354, "learning_rate": 1.7988254906942115e-08, "loss": 0.1249, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.3211069375022281, "learning_rate": 1.5670071526936447e-08, "loss": 0.1247, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.3169127465399384, "learning_rate": 1.3511682316509344e-08, "loss": 0.1326, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.33371907951672325, "learning_rate": 1.1513104534086605e-08, "loss": 0.1367, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.31915236878086034, "learning_rate": 9.67435416023843e-09, "loss": 0.1268, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.33150840536244774, "learning_rate": 7.995445897566178e-09, "loss": 0.1505, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.33270657883776916, "learning_rate": 6.476393170578021e-09, "loss": 0.126, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.3088554099315791, "learning_rate": 5.11720812557348e-09, "loss": 0.1376, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.3189517339132153, "learning_rate": 3.917901630563492e-09, "loss": 0.134, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.3294275106190296, "learning_rate": 2.878483275170485e-09, "loss": 0.1254, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.32356063640002375, "learning_rate": 1.998961370555108e-09, "loss": 0.1358, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.29738536805182336, "learning_rate": 1.2793429493518361e-09, "loss": 0.122, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.3166537652118685, "learning_rate": 7.196337656112384e-10, "loss": 0.1422, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.34169477305031487, "learning_rate": 3.198382947511292e-10, "loss": 0.116, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.3147224882257325, "learning_rate": 7.995973352770137e-11, "loss": 0.1369, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.29844047836937626, "learning_rate": 0.0, "loss": 0.1308, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.191822569796272e+18, "train_loss": 0.39378638465998145, "train_runtime": 17906.8088, "train_samples_per_second": 8.823, "train_steps_per_second": 0.069 } ], "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": 1.191822569796272e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }