{ "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": 9.22272866003907, "learning_rate": 3.2258064516129035e-07, "loss": 0.8179, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 9.510668129664563, "learning_rate": 6.451612903225807e-07, "loss": 0.8284, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 9.269138969668033, "learning_rate": 9.67741935483871e-07, "loss": 0.8218, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 8.98648149789598, "learning_rate": 1.2903225806451614e-06, "loss": 0.8106, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 9.007525192425426, "learning_rate": 1.6129032258064516e-06, "loss": 0.8098, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 8.953724202161233, "learning_rate": 1.935483870967742e-06, "loss": 0.8087, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 6.6349078366768, "learning_rate": 2.2580645161290324e-06, "loss": 0.7269, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 6.4455214473924896, "learning_rate": 2.580645161290323e-06, "loss": 0.7278, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 3.700721910863217, "learning_rate": 2.903225806451613e-06, "loss": 0.6658, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 3.382921478830033, "learning_rate": 3.225806451612903e-06, "loss": 0.6479, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 3.067116135679075, "learning_rate": 3.548387096774194e-06, "loss": 0.65, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.091702824115461, "learning_rate": 3.870967741935484e-06, "loss": 0.5893, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.107551967893217, "learning_rate": 4.193548387096774e-06, "loss": 0.5797, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.497717723912128, "learning_rate": 4.516129032258065e-06, "loss": 0.5584, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.0308392748769784, "learning_rate": 4.838709677419355e-06, "loss": 0.5532, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.3150406158774928, "learning_rate": 5.161290322580646e-06, "loss": 0.4942, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 3.1542116365327653, "learning_rate": 5.483870967741935e-06, "loss": 0.4787, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.5778818546675684, "learning_rate": 5.806451612903226e-06, "loss": 0.4718, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.4879442518162305, "learning_rate": 6.129032258064517e-06, "loss": 0.4389, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.505137060395917, "learning_rate": 6.451612903225806e-06, "loss": 0.4414, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.1995169852902898, "learning_rate": 6.774193548387097e-06, "loss": 0.4261, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 0.9818404399868936, "learning_rate": 7.096774193548388e-06, "loss": 0.4059, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 0.8726304958793515, "learning_rate": 7.4193548387096784e-06, "loss": 0.3937, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.8300510757478305, "learning_rate": 7.741935483870968e-06, "loss": 0.388, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8050804468735354, "learning_rate": 8.064516129032258e-06, "loss": 0.3773, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.7188315479494738, "learning_rate": 8.387096774193549e-06, "loss": 0.373, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.7010098512098606, "learning_rate": 8.70967741935484e-06, "loss": 0.3572, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.7707615083341361, "learning_rate": 9.03225806451613e-06, "loss": 0.3588, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.6957435343679395, "learning_rate": 9.35483870967742e-06, "loss": 0.3614, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7892242043169693, "learning_rate": 9.67741935483871e-06, "loss": 0.3576, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6690175738007385, "learning_rate": 1e-05, "loss": 0.3418, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.5925289946536778, "learning_rate": 1.0322580645161291e-05, "loss": 0.3498, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7101703866162864, "learning_rate": 1.0645161290322582e-05, "loss": 0.3219, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.5962452189913015, "learning_rate": 1.096774193548387e-05, "loss": 0.3216, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.5688070708878626, "learning_rate": 1.1290322580645164e-05, "loss": 0.3216, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.7192652566031785, "learning_rate": 1.1612903225806453e-05, "loss": 0.3104, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5857811514778956, "learning_rate": 1.1935483870967743e-05, "loss": 0.3252, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.583812469840486, "learning_rate": 1.2258064516129034e-05, "loss": 0.3068, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.7766725104698864, "learning_rate": 1.2580645161290324e-05, "loss": 0.3142, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5703050877982679, "learning_rate": 1.2903225806451613e-05, "loss": 0.3042, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7047358298004054, "learning_rate": 1.3225806451612903e-05, "loss": 0.2997, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5736115792864793, "learning_rate": 1.3548387096774194e-05, "loss": 0.3002, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5711198575458132, "learning_rate": 1.3870967741935486e-05, "loss": 0.3021, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5372661125242391, "learning_rate": 1.4193548387096776e-05, "loss": 0.3091, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.5312396460956719, "learning_rate": 1.4516129032258066e-05, "loss": 0.3023, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5238090749404466, "learning_rate": 1.4838709677419357e-05, "loss": 0.2902, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.5539017691624495, "learning_rate": 1.5161290322580646e-05, "loss": 0.2927, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5677537130658133, "learning_rate": 1.5483870967741936e-05, "loss": 0.2904, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6353590071728791, "learning_rate": 1.5806451612903226e-05, "loss": 0.295, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.580423927768243, "learning_rate": 1.6129032258064517e-05, "loss": 0.277, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.6169971206802884, "learning_rate": 1.6451612903225807e-05, "loss": 0.2931, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.5765721483226001, "learning_rate": 1.6774193548387098e-05, "loss": 0.2849, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.4977717048541061, "learning_rate": 1.7096774193548388e-05, "loss": 0.2776, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5129927271421575, "learning_rate": 1.741935483870968e-05, "loss": 0.2769, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.5902624330599975, "learning_rate": 1.774193548387097e-05, "loss": 0.281, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.7553555793541731, "learning_rate": 1.806451612903226e-05, "loss": 0.2931, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.636497436820258, "learning_rate": 1.838709677419355e-05, "loss": 0.2786, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.754911146494759, "learning_rate": 1.870967741935484e-05, "loss": 0.2866, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.7236138227378193, "learning_rate": 1.903225806451613e-05, "loss": 0.2727, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.640647122669408, "learning_rate": 1.935483870967742e-05, "loss": 0.2777, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5244097012588347, "learning_rate": 1.967741935483871e-05, "loss": 0.2849, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.6674874287397203, "learning_rate": 2e-05, "loss": 0.2822, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6762116223558502, "learning_rate": 2.0322580645161292e-05, "loss": 0.272, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.9813475161841626, "learning_rate": 2.0645161290322582e-05, "loss": 0.281, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.9998534553297128, "learning_rate": 2.0967741935483873e-05, "loss": 0.2622, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 1.1722289882447323, "learning_rate": 2.1290322580645163e-05, "loss": 0.2765, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.8171909704751019, "learning_rate": 2.161290322580645e-05, "loss": 0.259, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.5341213689152843, "learning_rate": 2.193548387096774e-05, "loss": 0.2764, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.7798596577627386, "learning_rate": 2.225806451612903e-05, "loss": 0.2706, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.0528066397216498, "learning_rate": 2.2580645161290328e-05, "loss": 0.2747, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.8058027575091212, "learning_rate": 2.2903225806451615e-05, "loss": 0.2742, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.8804683766161537, "learning_rate": 2.3225806451612906e-05, "loss": 0.2685, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.6698735278677905, "learning_rate": 2.3548387096774196e-05, "loss": 0.27, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6914524667841175, "learning_rate": 2.3870967741935486e-05, "loss": 0.2759, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.779173592607691, "learning_rate": 2.4193548387096777e-05, "loss": 0.2685, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.8536291572758393, "learning_rate": 2.4516129032258067e-05, "loss": 0.2731, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.6595812463713472, "learning_rate": 2.4838709677419358e-05, "loss": 0.263, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.6202169669489165, "learning_rate": 2.5161290322580648e-05, "loss": 0.2788, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7981389855835582, "learning_rate": 2.548387096774194e-05, "loss": 0.2721, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.7119333774374853, "learning_rate": 2.5806451612903226e-05, "loss": 0.2569, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.9867825841885851, "learning_rate": 2.6129032258064516e-05, "loss": 0.2624, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.9353262896279636, "learning_rate": 2.6451612903225806e-05, "loss": 0.2633, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.6296094130532366, "learning_rate": 2.6774193548387097e-05, "loss": 0.2695, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.6659131712458677, "learning_rate": 2.7096774193548387e-05, "loss": 0.2723, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.7179705870557332, "learning_rate": 2.7419354838709678e-05, "loss": 0.267, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7278604070613833, "learning_rate": 2.774193548387097e-05, "loss": 0.268, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7132386279609451, "learning_rate": 2.8064516129032262e-05, "loss": 0.2622, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.7445875230836768, "learning_rate": 2.8387096774193552e-05, "loss": 0.2681, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.7821871173666101, "learning_rate": 2.8709677419354843e-05, "loss": 0.2601, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.8656114572571715, "learning_rate": 2.9032258064516133e-05, "loss": 0.2667, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.7880993711369108, "learning_rate": 2.9354838709677423e-05, "loss": 0.2685, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.7634202990749578, "learning_rate": 2.9677419354838714e-05, "loss": 0.2629, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.5845781141551101, "learning_rate": 3.0000000000000004e-05, "loss": 0.2524, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7442873013437271, "learning_rate": 3.032258064516129e-05, "loss": 0.2777, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.9093926372216402, "learning_rate": 3.0645161290322585e-05, "loss": 0.282, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.5921883049756985, "learning_rate": 3.096774193548387e-05, "loss": 0.2568, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.6714963358617453, "learning_rate": 3.1290322580645166e-05, "loss": 0.2684, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.5950278091596247, "learning_rate": 3.161290322580645e-05, "loss": 0.2637, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.6022772941372133, "learning_rate": 3.193548387096774e-05, "loss": 0.273, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.610822448709745, "learning_rate": 3.2258064516129034e-05, "loss": 0.2722, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.6774557473713188, "learning_rate": 3.258064516129033e-05, "loss": 0.2688, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.7554291000273741, "learning_rate": 3.2903225806451614e-05, "loss": 0.2662, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.7884949295258094, "learning_rate": 3.322580645161291e-05, "loss": 0.2784, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.7814586526748156, "learning_rate": 3.3548387096774195e-05, "loss": 0.2765, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.574293919349437, "learning_rate": 3.387096774193549e-05, "loss": 0.2613, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.684453299601202, "learning_rate": 3.4193548387096776e-05, "loss": 0.268, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.9922204806021874, "learning_rate": 3.451612903225807e-05, "loss": 0.2832, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.9930460584871031, "learning_rate": 3.483870967741936e-05, "loss": 0.2622, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.6877935779376327, "learning_rate": 3.516129032258065e-05, "loss": 0.2643, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.6585131842959604, "learning_rate": 3.548387096774194e-05, "loss": 0.2439, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.6501625083889476, "learning_rate": 3.5806451612903225e-05, "loss": 0.2597, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.6749752455505992, "learning_rate": 3.612903225806452e-05, "loss": 0.2555, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.6240170489774001, "learning_rate": 3.6451612903225805e-05, "loss": 0.2625, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.6862204263814715, "learning_rate": 3.67741935483871e-05, "loss": 0.2632, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.6215013404450546, "learning_rate": 3.7096774193548386e-05, "loss": 0.2573, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.797845795075224, "learning_rate": 3.741935483870968e-05, "loss": 0.2783, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.8213074081661343, "learning_rate": 3.7741935483870974e-05, "loss": 0.2556, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.8502729383212448, "learning_rate": 3.806451612903226e-05, "loss": 0.2734, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.679314768444725, "learning_rate": 3.8387096774193555e-05, "loss": 0.2698, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.5803417560258282, "learning_rate": 3.870967741935484e-05, "loss": 0.2648, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.6938184734925226, "learning_rate": 3.9032258064516135e-05, "loss": 0.2664, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6014955448896496, "learning_rate": 3.935483870967742e-05, "loss": 0.2607, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.6224330867433312, "learning_rate": 3.9677419354838716e-05, "loss": 0.2539, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7146685472231018, "learning_rate": 4e-05, "loss": 0.2673, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.6033241047266144, "learning_rate": 3.9999920040266474e-05, "loss": 0.2646, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.5641881978846616, "learning_rate": 3.999968016170525e-05, "loss": 0.2563, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.5861295953329587, "learning_rate": 3.9999280366234394e-05, "loss": 0.2608, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.5609569135438455, "learning_rate": 3.999872065705065e-05, "loss": 0.2507, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.580622213544689, "learning_rate": 3.999800103862945e-05, "loss": 0.2587, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6379250873313457, "learning_rate": 3.9997121516724834e-05, "loss": 0.265, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.6104065057612742, "learning_rate": 3.999608209836944e-05, "loss": 0.2542, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.48177627136751755, "learning_rate": 3.999488279187443e-05, "loss": 0.2677, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.519922176273831, "learning_rate": 3.9993523606829425e-05, "loss": 0.2565, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.4745164310555371, "learning_rate": 3.9992004554102435e-05, "loss": 0.2605, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.4939004309744369, "learning_rate": 3.999032564583976e-05, "loss": 0.2479, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.4594834213486646, "learning_rate": 3.998848689546591e-05, "loss": 0.259, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.4840869733452805, "learning_rate": 3.9986488317683496e-05, "loss": 0.2617, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.5125565740627035, "learning_rate": 3.9984329928473067e-05, "loss": 0.2578, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.5645745010610987, "learning_rate": 3.998201174509306e-05, "loss": 0.2634, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6016771539219601, "learning_rate": 3.997953378607961e-05, "loss": 0.2525, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.5304154453249329, "learning_rate": 3.9976896071246403e-05, "loss": 0.2748, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.4950220229384847, "learning_rate": 3.997409862168454e-05, "loss": 0.2524, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.6136379112701027, "learning_rate": 3.997114145976237e-05, "loss": 0.2478, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5309545996505387, "learning_rate": 3.9968024609125245e-05, "loss": 0.2597, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6141025658978327, "learning_rate": 3.996474809469545e-05, "loss": 0.2588, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.5888991706132225, "learning_rate": 3.996131194267189e-05, "loss": 0.2609, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.46496012377918505, "learning_rate": 3.995771618052995e-05, "loss": 0.2397, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.5208421311424403, "learning_rate": 3.9953960837021256e-05, "loss": 0.2562, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.6037073216013094, "learning_rate": 3.995004594217343e-05, "loss": 0.2531, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.49001579286563113, "learning_rate": 3.994597152728987e-05, "loss": 0.2537, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6700234530041979, "learning_rate": 3.994173762494947e-05, "loss": 0.2505, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.5621548498109604, "learning_rate": 3.9937344269006424e-05, "loss": 0.2407, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.5079773258859823, "learning_rate": 3.993279149458988e-05, "loss": 0.252, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.6183270128741118, "learning_rate": 3.9928079338103695e-05, "loss": 0.2464, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.6201695700465474, "learning_rate": 3.992320783722616e-05, "loss": 0.2453, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.46322099553168733, "learning_rate": 3.991817703090965e-05, "loss": 0.2606, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.5236919587965687, "learning_rate": 3.991298695938038e-05, "loss": 0.2501, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.47378957117862686, "learning_rate": 3.9907637664138e-05, "loss": 0.2514, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.5123783320412728, "learning_rate": 3.990212918795534e-05, "loss": 0.2548, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.37002482592979596, "learning_rate": 3.9896461574878036e-05, "loss": 0.2342, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.5193919301213603, "learning_rate": 3.989063487022416e-05, "loss": 0.2525, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.562903747542235, "learning_rate": 3.9884649120583903e-05, "loss": 0.2522, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.47720725556329924, "learning_rate": 3.987850437381915e-05, "loss": 0.2489, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.46318868902959304, "learning_rate": 3.987220067906313e-05, "loss": 0.2417, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.44313021914181716, "learning_rate": 3.986573808672002e-05, "loss": 0.2477, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.4118009013938669, "learning_rate": 3.9859116648464534e-05, "loss": 0.2416, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.4603426454613012, "learning_rate": 3.985233641724152e-05, "loss": 0.2365, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.39140142120806976, "learning_rate": 3.984539744726554e-05, "loss": 0.248, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.467547677118322, "learning_rate": 3.983829979402038e-05, "loss": 0.2704, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.3915446794567895, "learning_rate": 3.983104351425871e-05, "loss": 0.2496, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6037893613232374, "learning_rate": 3.982362866600154e-05, "loss": 0.2531, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6602401526133391, "learning_rate": 3.9816055308537806e-05, "loss": 0.2527, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.5172035778693992, "learning_rate": 3.980832350242388e-05, "loss": 0.2619, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5084122033927483, "learning_rate": 3.980043330948306e-05, "loss": 0.2435, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.6101794280942493, "learning_rate": 3.9792384792805124e-05, "loss": 0.2564, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5375804343729239, "learning_rate": 3.978417801674579e-05, "loss": 0.256, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.5044912869083152, "learning_rate": 3.9775813046926244e-05, "loss": 0.2527, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.4161714734580941, "learning_rate": 3.976728995023254e-05, "loss": 0.2432, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.43408391456823103, "learning_rate": 3.975860879481514e-05, "loss": 0.2445, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.3847725306176431, "learning_rate": 3.974976965008833e-05, "loss": 0.2453, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.3817623151026022, "learning_rate": 3.9740772586729674e-05, "loss": 0.2504, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.40966476659389345, "learning_rate": 3.973161767667946e-05, "loss": 0.25, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.45080397872775124, "learning_rate": 3.972230499314009e-05, "loss": 0.2507, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.47082995960032525, "learning_rate": 3.9712834610575545e-05, "loss": 0.2483, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.49998214438789734, "learning_rate": 3.9703206604710746e-05, "loss": 0.2531, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.3924547828221678, "learning_rate": 3.969342105253098e-05, "loss": 0.2451, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.4255545932850788, "learning_rate": 3.9683478032281246e-05, "loss": 0.2413, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.406009870969209, "learning_rate": 3.967337762346568e-05, "loss": 0.243, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.4571511602490343, "learning_rate": 3.9663119906846885e-05, "loss": 0.2533, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.4361229730301623, "learning_rate": 3.965270496444528e-05, "loss": 0.2356, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.41574770537829303, "learning_rate": 3.9642132879538465e-05, "loss": 0.2475, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.4391679885023987, "learning_rate": 3.9631403736660566e-05, "loss": 0.2537, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.4077376983154671, "learning_rate": 3.962051762160151e-05, "loss": 0.2457, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.4484110057678974, "learning_rate": 3.960947462140638e-05, "loss": 0.246, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.4178189266235399, "learning_rate": 3.959827482437472e-05, "loss": 0.2587, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.4336517090635402, "learning_rate": 3.958691832005981e-05, "loss": 0.2602, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.3756135115840068, "learning_rate": 3.9575405199267944e-05, "loss": 0.2557, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.44121985209843617, "learning_rate": 3.956373555405774e-05, "loss": 0.253, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.4685169519018023, "learning_rate": 3.955190947773937e-05, "loss": 0.2505, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.413752390637991, "learning_rate": 3.9539927064873824e-05, "loss": 0.2386, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.4073618527465767, "learning_rate": 3.952778841127214e-05, "loss": 0.2404, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.3757232954324718, "learning_rate": 3.95154936139947e-05, "loss": 0.2452, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5118332521414544, "learning_rate": 3.950304277135034e-05, "loss": 0.2449, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.42720665705021543, "learning_rate": 3.94904359828957e-05, "loss": 0.252, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.43801096418042906, "learning_rate": 3.94776733494343e-05, "loss": 0.2332, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.49571776979301796, "learning_rate": 3.9464754973015826e-05, "loss": 0.2365, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.4840157918372083, "learning_rate": 3.9451680956935275e-05, "loss": 0.2451, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.368608110045104, "learning_rate": 3.943845140573213e-05, "loss": 0.2508, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.3924989563698997, "learning_rate": 3.942506642518952e-05, "loss": 0.2427, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.47180428832528887, "learning_rate": 3.9411526122333396e-05, "loss": 0.2499, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.41375907449630145, "learning_rate": 3.939783060543167e-05, "loss": 0.2419, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.39610706393432954, "learning_rate": 3.938397998399333e-05, "loss": 0.2532, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.45786659131288837, "learning_rate": 3.936997436876756e-05, "loss": 0.239, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.4641073316995611, "learning_rate": 3.935581387174289e-05, "loss": 0.2283, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.3857182424883212, "learning_rate": 3.9341498606146295e-05, "loss": 0.2425, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.5820678561306306, "learning_rate": 3.932702868644224e-05, "loss": 0.2428, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5220513139676588, "learning_rate": 3.931240422833181e-05, "loss": 0.2458, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.35322464071287873, "learning_rate": 3.9297625348751806e-05, "loss": 0.2422, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5023575441374689, "learning_rate": 3.9282692165873744e-05, "loss": 0.2425, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.4351165005834244, "learning_rate": 3.9267604799102945e-05, "loss": 0.2445, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.4313985064706949, "learning_rate": 3.9252363369077615e-05, "loss": 0.2438, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.46275366975080107, "learning_rate": 3.9236967997667796e-05, "loss": 0.2506, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.455587001509524, "learning_rate": 3.9221418807974496e-05, "loss": 0.2431, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.4759330901680354, "learning_rate": 3.92057159243286e-05, "loss": 0.2488, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.3902041137632925, "learning_rate": 3.9189859472289956e-05, "loss": 0.2438, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.4881202983773955, "learning_rate": 3.9173849578646324e-05, "loss": 0.2404, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.38416580651113724, "learning_rate": 3.9157686371412395e-05, "loss": 0.2441, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.3971508838300705, "learning_rate": 3.914136997982874e-05, "loss": 0.2329, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.414907678228531, "learning_rate": 3.912490053436079e-05, "loss": 0.2485, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.44384293161793176, "learning_rate": 3.9108278166697805e-05, "loss": 0.2481, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.3894662071961911, "learning_rate": 3.909150300975178e-05, "loss": 0.2461, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4853378674750463, "learning_rate": 3.907457519765642e-05, "loss": 0.244, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.3664129988048841, "learning_rate": 3.905749486576607e-05, "loss": 0.2406, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.4452550952700585, "learning_rate": 3.90402621506546e-05, "loss": 0.2396, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.44661230575190397, "learning_rate": 3.902287719011435e-05, "loss": 0.26, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.41923323890864805, "learning_rate": 3.900534012315499e-05, "loss": 0.2358, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.3817737104747034, "learning_rate": 3.8987651090002454e-05, "loss": 0.2426, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.4973918166549352, "learning_rate": 3.896981023209777e-05, "loss": 0.242, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4225037240818989, "learning_rate": 3.8951817692095966e-05, "loss": 0.2369, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.42638031307310154, "learning_rate": 3.893367361386491e-05, "loss": 0.2433, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.5396070069248041, "learning_rate": 3.891537814248417e-05, "loss": 0.2309, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.44112229174207584, "learning_rate": 3.889693142424384e-05, "loss": 0.2383, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.40987098296175206, "learning_rate": 3.8878333606643405e-05, "loss": 0.2386, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.4853676245829324, "learning_rate": 3.885958483839049e-05, "loss": 0.2356, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.4425852505875759, "learning_rate": 3.8840685269399786e-05, "loss": 0.2303, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.4412789362238925, "learning_rate": 3.882163505079171e-05, "loss": 0.242, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.35488279488302116, "learning_rate": 3.880243433489132e-05, "loss": 0.2413, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5341472680395881, "learning_rate": 3.878308327522702e-05, "loss": 0.2106, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.48163658418565747, "learning_rate": 3.876358202652936e-05, "loss": 0.2147, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.43338171522561364, "learning_rate": 3.8743930744729835e-05, "loss": 0.2159, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.4617685022071543, "learning_rate": 3.8724129586959535e-05, "loss": 0.214, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.3823513347313309, "learning_rate": 3.870417871154801e-05, "loss": 0.2083, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.4733797882094991, "learning_rate": 3.868407827802192e-05, "loss": 0.2048, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.3443441904425595, "learning_rate": 3.8663828447103804e-05, "loss": 0.2101, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.37453988397093013, "learning_rate": 3.8643429380710765e-05, "loss": 0.2053, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.4171665354489152, "learning_rate": 3.862288124195319e-05, "loss": 0.2157, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.3749272918787455, "learning_rate": 3.8602184195133464e-05, "loss": 0.2102, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.4161558040283633, "learning_rate": 3.8581338405744604e-05, "loss": 0.2128, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.3553101226395537, "learning_rate": 3.8560344040468996e-05, "loss": 0.2195, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.38030600614914584, "learning_rate": 3.853920126717703e-05, "loss": 0.2189, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.3222027238224297, "learning_rate": 3.851791025492574e-05, "loss": 0.2036, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.38447655181420387, "learning_rate": 3.8496471173957515e-05, "loss": 0.2085, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.4030868869703552, "learning_rate": 3.847488419569866e-05, "loss": 0.2133, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.30993559949147254, "learning_rate": 3.8453149492758077e-05, "loss": 0.2089, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.4857529587276105, "learning_rate": 3.8431267238925886e-05, "loss": 0.2172, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.35257767075242796, "learning_rate": 3.840923760917199e-05, "loss": 0.2111, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.509467020909736, "learning_rate": 3.838706077964473e-05, "loss": 0.2077, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.44599418341849684, "learning_rate": 3.836473692766944e-05, "loss": 0.2165, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.35218738032221886, "learning_rate": 3.834226623174705e-05, "loss": 0.2176, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.4295991074096429, "learning_rate": 3.831964887155264e-05, "loss": 0.223, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.3934031442311879, "learning_rate": 3.829688502793403e-05, "loss": 0.2082, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.3891652414124039, "learning_rate": 3.827397488291029e-05, "loss": 0.217, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.37484563479142086, "learning_rate": 3.8250918619670343e-05, "loss": 0.2034, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.4372061431308479, "learning_rate": 3.822771642257145e-05, "loss": 0.214, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.36300556281504975, "learning_rate": 3.820436847713776e-05, "loss": 0.2114, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.35626773070912143, "learning_rate": 3.8180874970058826e-05, "loss": 0.2049, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.371375777567871, "learning_rate": 3.8157236089188103e-05, "loss": 0.2091, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.3898869266595605, "learning_rate": 3.813345202354145e-05, "loss": 0.2119, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.42174253042207804, "learning_rate": 3.810952296329563e-05, "loss": 0.2162, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.39585006891744207, "learning_rate": 3.808544909978676e-05, "loss": 0.2199, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.3633287908642114, "learning_rate": 3.806123062550882e-05, "loss": 0.2157, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.4208829750093641, "learning_rate": 3.803686773411208e-05, "loss": 0.2106, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.39587473871435824, "learning_rate": 3.801236062040158e-05, "loss": 0.2103, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.45507027521442356, "learning_rate": 3.798770948033553e-05, "loss": 0.209, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4146703553296298, "learning_rate": 3.796291451102381e-05, "loss": 0.2213, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.37458659437585184, "learning_rate": 3.793797591072631e-05, "loss": 0.2082, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.43229435360783164, "learning_rate": 3.791289387885144e-05, "loss": 0.2127, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.42979299313293023, "learning_rate": 3.788766861595443e-05, "loss": 0.2067, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.35816768474833, "learning_rate": 3.7862300323735835e-05, "loss": 0.2195, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.4163932815861454, "learning_rate": 3.783678920503983e-05, "loss": 0.209, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.434508422074532, "learning_rate": 3.781113546385265e-05, "loss": 0.2138, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.37373403746141826, "learning_rate": 3.7785339305300916e-05, "loss": 0.2233, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.44852159670327624, "learning_rate": 3.7759400935650025e-05, "loss": 0.2129, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.34691868329276065, "learning_rate": 3.77333205623025e-05, "loss": 0.2269, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.3643304950841284, "learning_rate": 3.7707098393796295e-05, "loss": 0.2183, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.3688074391819701, "learning_rate": 3.7680734639803185e-05, "loss": 0.2149, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.31207863874062436, "learning_rate": 3.765422951112704e-05, "loss": 0.2098, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.3914208722102077, "learning_rate": 3.762758321970216e-05, "loss": 0.2121, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.34055947328760505, "learning_rate": 3.7600795978591584e-05, "loss": 0.2136, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.3176711522276666, "learning_rate": 3.757386800198538e-05, "loss": 0.2176, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.340074528007548, "learning_rate": 3.7546799505198925e-05, "loss": 0.2024, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.33992046792621516, "learning_rate": 3.7519590704671197e-05, "loss": 0.2133, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.32242395136183627, "learning_rate": 3.749224181796305e-05, "loss": 0.2058, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.35023503678068524, "learning_rate": 3.746475306375545e-05, "loss": 0.2226, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.35347895499126164, "learning_rate": 3.743712466184774e-05, "loss": 0.214, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.31883192182057163, "learning_rate": 3.7409356833155885e-05, "loss": 0.2087, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.382115638852244, "learning_rate": 3.73814497997107e-05, "loss": 0.2182, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.360248022580084, "learning_rate": 3.7353403784656095e-05, "loss": 0.2207, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.3774002580936352, "learning_rate": 3.732521901224724e-05, "loss": 0.216, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.41570551237017567, "learning_rate": 3.7296895707848844e-05, "loss": 0.2263, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.35156935962940133, "learning_rate": 3.7268434097933275e-05, "loss": 0.2107, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.37033384968470984, "learning_rate": 3.723983441007882e-05, "loss": 0.2191, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.37917623037638365, "learning_rate": 3.721109687296781e-05, "loss": 0.2093, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.3377173932526813, "learning_rate": 3.718222171638484e-05, "loss": 0.2065, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.4082977410362204, "learning_rate": 3.715320917121488e-05, "loss": 0.2217, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.3189055466286939, "learning_rate": 3.712405946944149e-05, "loss": 0.2077, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.39450355458854847, "learning_rate": 3.709477284414488e-05, "loss": 0.2185, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.37562155612251863, "learning_rate": 3.7065349529500136e-05, "loss": 0.2117, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.35129485568791563, "learning_rate": 3.7035789760775305e-05, "loss": 0.2102, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.3827837900931861, "learning_rate": 3.70060937743295e-05, "loss": 0.2107, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.3879588423577542, "learning_rate": 3.6976261807611045e-05, "loss": 0.2146, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.3616316380376413, "learning_rate": 3.694629409915555e-05, "loss": 0.2143, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.3768709873452954, "learning_rate": 3.691619088858401e-05, "loss": 0.2135, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.3700231305122154, "learning_rate": 3.68859524166009e-05, "loss": 0.2119, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.35579775122413065, "learning_rate": 3.6855578924992226e-05, "loss": 0.2305, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.4606833285193492, "learning_rate": 3.6825070656623626e-05, "loss": 0.212, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.3995281369886274, "learning_rate": 3.67944278554384e-05, "loss": 0.2214, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.3452871973970421, "learning_rate": 3.676365076645557e-05, "loss": 0.2216, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4046277911643185, "learning_rate": 3.673273963576791e-05, "loss": 0.2117, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.33017098295357133, "learning_rate": 3.670169471054001e-05, "loss": 0.2201, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.4273884990619142, "learning_rate": 3.6670516239006254e-05, "loss": 0.2092, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.3175428548575478, "learning_rate": 3.663920447046888e-05, "loss": 0.2047, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.39465910775932433, "learning_rate": 3.6607759655295954e-05, "loss": 0.2168, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.33413239609190665, "learning_rate": 3.657618204491937e-05, "loss": 0.216, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.33733101975722707, "learning_rate": 3.6544471891832875e-05, "loss": 0.2116, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.3255714577415934, "learning_rate": 3.6512629449589983e-05, "loss": 0.2125, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.3240735159701378, "learning_rate": 3.6480654972802045e-05, "loss": 0.2164, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.3415339675676527, "learning_rate": 3.644854871713611e-05, "loss": 0.2075, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.38185404691283903, "learning_rate": 3.6416310939312924e-05, "loss": 0.2023, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.3044966847657225, "learning_rate": 3.638394189710493e-05, "loss": 0.2084, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.35159169760066544, "learning_rate": 3.635144184933412e-05, "loss": 0.2135, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.3075943491846846, "learning_rate": 3.6318811055869994e-05, "loss": 0.2199, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.3897857457409495, "learning_rate": 3.628604977762752e-05, "loss": 0.2167, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.4155001929080949, "learning_rate": 3.6253158276565004e-05, "loss": 0.211, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.3331935640401685, "learning_rate": 3.6220136815682016e-05, "loss": 0.2143, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.36238602824269184, "learning_rate": 3.618698565901727e-05, "loss": 0.2115, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.3210954093488501, "learning_rate": 3.615370507164654e-05, "loss": 0.2082, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.33984450854378545, "learning_rate": 3.61202953196805e-05, "loss": 0.2125, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.30532499350308145, "learning_rate": 3.6086756670262654e-05, "loss": 0.2067, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.381936870312085, "learning_rate": 3.6053089391567135e-05, "loss": 0.2113, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.31753054522355223, "learning_rate": 3.601929375279662e-05, "loss": 0.2101, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.37566657748497206, "learning_rate": 3.598537002418012e-05, "loss": 0.2041, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.30907540107094106, "learning_rate": 3.5951318476970885e-05, "loss": 0.2093, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.38601102482074806, "learning_rate": 3.591713938344416e-05, "loss": 0.2166, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.31476188753780365, "learning_rate": 3.588283301689507e-05, "loss": 0.2068, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.33164962713533586, "learning_rate": 3.5848399651636424e-05, "loss": 0.2058, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.33035684316400277, "learning_rate": 3.5813839562996473e-05, "loss": 0.2063, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.341051472725903, "learning_rate": 3.5779153027316775e-05, "loss": 0.2182, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.3636947884725443, "learning_rate": 3.574434032194994e-05, "loss": 0.2117, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.3735323316320995, "learning_rate": 3.5709401725257436e-05, "loss": 0.2147, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.34876322478742694, "learning_rate": 3.5674337516607346e-05, "loss": 0.2157, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.3449095771502271, "learning_rate": 3.563914797637216e-05, "loss": 0.2021, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.34767103256835474, "learning_rate": 3.560383338592649e-05, "loss": 0.2122, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.32400727326709805, "learning_rate": 3.556839402764487e-05, "loss": 0.2131, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.32699458264496384, "learning_rate": 3.553283018489946e-05, "loss": 0.2076, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.37820370404957593, "learning_rate": 3.54971421420578e-05, "loss": 0.2065, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.34061582663047746, "learning_rate": 3.5461330184480524e-05, "loss": 0.2216, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.32113351329893286, "learning_rate": 3.54253945985191e-05, "loss": 0.2142, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.3574989808315918, "learning_rate": 3.5389335671513524e-05, "loss": 0.2112, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.309486337828358, "learning_rate": 3.5353153691789986e-05, "loss": 0.2161, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.3041866897174127, "learning_rate": 3.531684894865866e-05, "loss": 0.213, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.36727213676676074, "learning_rate": 3.528042173241128e-05, "loss": 0.2107, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.3139524488400728, "learning_rate": 3.524387233431892e-05, "loss": 0.2045, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.3349018000686865, "learning_rate": 3.520720104662958e-05, "loss": 0.209, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.3195906617948048, "learning_rate": 3.5170408162565904e-05, "loss": 0.2148, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.31157951536287204, "learning_rate": 3.513349397632281e-05, "loss": 0.2062, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.3232130839193365, "learning_rate": 3.5096458783065145e-05, "loss": 0.2208, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.32247142281626606, "learning_rate": 3.505930287892533e-05, "loss": 0.2105, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.2987077346046711, "learning_rate": 3.502202656100099e-05, "loss": 0.2074, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.3531351247799071, "learning_rate": 3.498463012735256e-05, "loss": 0.2143, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.3048230218293405, "learning_rate": 3.494711387700094e-05, "loss": 0.2134, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.31179476087447316, "learning_rate": 3.490947810992505e-05, "loss": 0.2015, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.3645169523473513, "learning_rate": 3.48717231270595e-05, "loss": 0.2113, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.36245740649287744, "learning_rate": 3.483384923029211e-05, "loss": 0.2138, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.3484302484985141, "learning_rate": 3.479585672246156e-05, "loss": 0.2122, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.3424264382902805, "learning_rate": 3.4757745907354924e-05, "loss": 0.2102, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.35128242659730213, "learning_rate": 3.471951708970527e-05, "loss": 0.2052, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.301552969392606, "learning_rate": 3.468117057518921e-05, "loss": 0.2119, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.3245905007794217, "learning_rate": 3.4642706670424426e-05, "loss": 0.2147, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.3325460714669985, "learning_rate": 3.460412568296731e-05, "loss": 0.2127, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.34113842098712605, "learning_rate": 3.456542792131039e-05, "loss": 0.2102, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.38100997410739035, "learning_rate": 3.4526613694879936e-05, "loss": 0.2127, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.3310025718585502, "learning_rate": 3.448768331403348e-05, "loss": 0.2136, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.35204525920300694, "learning_rate": 3.44486370900573e-05, "loss": 0.2055, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.3268991982164563, "learning_rate": 3.440947533516396e-05, "loss": 0.2088, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.3760421226576196, "learning_rate": 3.4370198362489816e-05, "loss": 0.2124, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.3465297948593322, "learning_rate": 3.43308064860925e-05, "loss": 0.2176, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.32101419140534126, "learning_rate": 3.4291300020948393e-05, "loss": 0.2088, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.33944125877531883, "learning_rate": 3.425167928295015e-05, "loss": 0.2197, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.3127165480366456, "learning_rate": 3.421194458890411e-05, "loss": 0.2097, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.3221243780854353, "learning_rate": 3.4172096256527865e-05, "loss": 0.2151, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.28086260711811323, "learning_rate": 3.4132134604447595e-05, "loss": 0.2111, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.31935535950250493, "learning_rate": 3.409205995219561e-05, "loss": 0.2251, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.3015748541612116, "learning_rate": 3.4051872620207765e-05, "loss": 0.2111, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.31560891390355134, "learning_rate": 3.40115729298209e-05, "loss": 0.214, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.27749343518319103, "learning_rate": 3.397116120327025e-05, "loss": 0.2114, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.3302409016806463, "learning_rate": 3.3930637763686916e-05, "loss": 0.2059, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.30523520105377905, "learning_rate": 3.389000293509524e-05, "loss": 0.2079, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.2976207337358605, "learning_rate": 3.3849257042410225e-05, "loss": 0.2196, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.2750487589638169, "learning_rate": 3.380840041143494e-05, "loss": 0.2143, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.30098247045017756, "learning_rate": 3.376743336885792e-05, "loss": 0.2102, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.28431376774085215, "learning_rate": 3.372635624225055e-05, "loss": 0.2063, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.2816499197997471, "learning_rate": 3.3685169360064445e-05, "loss": 0.2015, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.2877968963820655, "learning_rate": 3.3643873051628804e-05, "loss": 0.2074, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.27830802895164947, "learning_rate": 3.3602467647147814e-05, "loss": 0.212, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.3264553579381515, "learning_rate": 3.356095347769799e-05, "loss": 0.206, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.3387968753805478, "learning_rate": 3.351933087522552e-05, "loss": 0.2085, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.40237361276500977, "learning_rate": 3.3477600172543626e-05, "loss": 0.2208, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.33080222908717377, "learning_rate": 3.3435761703329894e-05, "loss": 0.2162, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.35006698104681183, "learning_rate": 3.3393815802123606e-05, "loss": 0.2012, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.31457149451004024, "learning_rate": 3.335176280432308e-05, "loss": 0.2083, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.3125769797257544, "learning_rate": 3.330960304618295e-05, "loss": 0.2065, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.31413590861244844, "learning_rate": 3.326733686481153e-05, "loss": 0.2009, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.3322913193492305, "learning_rate": 3.3224964598168084e-05, "loss": 0.2124, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.29197594356923257, "learning_rate": 3.318248658506012e-05, "loss": 0.2121, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.33049897246386056, "learning_rate": 3.313990316514069e-05, "loss": 0.2062, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.29731447600559374, "learning_rate": 3.309721467890571e-05, "loss": 0.211, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.313759650355192, "learning_rate": 3.305442146769115e-05, "loss": 0.2095, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.3464121960606226, "learning_rate": 3.30115238736704e-05, "loss": 0.2153, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.28123864056981457, "learning_rate": 3.296852223985148e-05, "loss": 0.2084, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.37490756814738857, "learning_rate": 3.2925416910074315e-05, "loss": 0.2224, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.2978449679179614, "learning_rate": 3.288220822900796e-05, "loss": 0.2105, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.32174699734911166, "learning_rate": 3.283889654214788e-05, "loss": 0.2071, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.31121967458992655, "learning_rate": 3.279548219581317e-05, "loss": 0.2188, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.3228337668368914, "learning_rate": 3.275196553714379e-05, "loss": 0.2088, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.3289585206253377, "learning_rate": 3.270834691409778e-05, "loss": 0.2019, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.30353352331310324, "learning_rate": 3.266462667544849e-05, "loss": 0.2077, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.3040570644550453, "learning_rate": 3.262080517078178e-05, "loss": 0.2178, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.30712955381889645, "learning_rate": 3.257688275049323e-05, "loss": 0.2138, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.3111335261272498, "learning_rate": 3.253285976578535e-05, "loss": 0.2086, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.35874296614185186, "learning_rate": 3.2488736568664756e-05, "loss": 0.2033, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.30124984682944134, "learning_rate": 3.244451351193935e-05, "loss": 0.2156, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.3176712948074369, "learning_rate": 3.240019094921551e-05, "loss": 0.2017, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.3149480969997968, "learning_rate": 3.235576923489527e-05, "loss": 0.2115, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.29989699828766014, "learning_rate": 3.2311248724173476e-05, "loss": 0.209, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.33453055039648144, "learning_rate": 3.226662977303494e-05, "loss": 0.2125, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.3169502668902467, "learning_rate": 3.2221912738251626e-05, "loss": 0.2099, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.3104246824519511, "learning_rate": 3.2177097977379736e-05, "loss": 0.2107, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.30254932105068233, "learning_rate": 3.21321858487569e-05, "loss": 0.2095, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.28120007902538807, "learning_rate": 3.208717671149931e-05, "loss": 0.2037, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.2870810519066614, "learning_rate": 3.204207092549882e-05, "loss": 0.2119, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.35321111521707355, "learning_rate": 3.19968688514201e-05, "loss": 0.2127, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.2922199998583453, "learning_rate": 3.195157085069774e-05, "loss": 0.2048, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.32746517167290895, "learning_rate": 3.190617728553332e-05, "loss": 0.2048, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.3654068970466987, "learning_rate": 3.1860688518892606e-05, "loss": 0.2178, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.3915629780144645, "learning_rate": 3.181510491450254e-05, "loss": 0.2172, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.36191589046999495, "learning_rate": 3.176942683684842e-05, "loss": 0.2054, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.32928690822366335, "learning_rate": 3.1723654651170934e-05, "loss": 0.2087, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.31595210363572873, "learning_rate": 3.167778872346327e-05, "loss": 0.2056, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.316812220044355, "learning_rate": 3.163182942046815e-05, "loss": 0.2113, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.3714539015662232, "learning_rate": 3.158577710967494e-05, "loss": 0.2176, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.304921666749915, "learning_rate": 3.153963215931669e-05, "loss": 0.2052, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.34299558461508506, "learning_rate": 3.14933949383672e-05, "loss": 0.2131, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.3269144708031604, "learning_rate": 3.144706581653805e-05, "loss": 0.2121, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.3226377628041256, "learning_rate": 3.140064516427566e-05, "loss": 0.21, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.3718429675034078, "learning_rate": 3.135413335275833e-05, "loss": 0.213, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.3253513729901997, "learning_rate": 3.130753075389327e-05, "loss": 0.2067, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.3573286621310272, "learning_rate": 3.1260837740313625e-05, "loss": 0.2101, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.3125400746118568, "learning_rate": 3.121405468537547e-05, "loss": 0.2046, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.3762721219053282, "learning_rate": 3.116718196315488e-05, "loss": 0.2082, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.2983905868550448, "learning_rate": 3.1120219948444894e-05, "loss": 0.2076, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.38519206056798294, "learning_rate": 3.107316901675252e-05, "loss": 0.2091, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3761732494267046, "learning_rate": 3.1026029544295745e-05, "loss": 0.2043, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.31171341523510515, "learning_rate": 3.097880190800057e-05, "loss": 0.2123, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.34662289119020084, "learning_rate": 3.093148648549788e-05, "loss": 0.2114, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.34851628187505207, "learning_rate": 3.088408365512055e-05, "loss": 0.213, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.2939745702639894, "learning_rate": 3.083659379590034e-05, "loss": 0.2208, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.3022820614311369, "learning_rate": 3.0789017287564913e-05, "loss": 0.2078, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.28476727144456965, "learning_rate": 3.074135451053475e-05, "loss": 0.2034, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.2851113033118369, "learning_rate": 3.069360584592015e-05, "loss": 0.2082, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.33249326214536357, "learning_rate": 3.064577167551816e-05, "loss": 0.2034, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.3254678385070541, "learning_rate": 3.059785238180953e-05, "loss": 0.2105, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.29217284986272524, "learning_rate": 3.054984834795566e-05, "loss": 0.208, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.30034423371882535, "learning_rate": 3.0501759957795537e-05, "loss": 0.2031, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.29762694293329567, "learning_rate": 3.0453587595842627e-05, "loss": 0.2046, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.2768327474111028, "learning_rate": 3.0405331647281856e-05, "loss": 0.1994, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.3233236681852982, "learning_rate": 3.0356992497966508e-05, "loss": 0.2033, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3433944936853487, "learning_rate": 3.0308570534415137e-05, "loss": 0.2095, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.36663179568067406, "learning_rate": 3.0260066143808467e-05, "loss": 0.2053, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.3204192015378988, "learning_rate": 3.021147971398632e-05, "loss": 0.2152, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.35334755853478295, "learning_rate": 3.0162811633444478e-05, "loss": 0.2098, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.31450809746088, "learning_rate": 3.0114062291331635e-05, "loss": 0.2056, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.31134074659380023, "learning_rate": 3.0065232077446217e-05, "loss": 0.2056, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.32505075404975986, "learning_rate": 3.001632138223332e-05, "loss": 0.2056, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.3151565020364147, "learning_rate": 2.9967330596781565e-05, "loss": 0.1774, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.32381275794561964, "learning_rate": 2.9918260112819952e-05, "loss": 0.1696, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.31755150172154584, "learning_rate": 2.9869110322714778e-05, "loss": 0.1692, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.3121490749085729, "learning_rate": 2.9819881619466447e-05, "loss": 0.1661, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.34820949487768127, "learning_rate": 2.9770574396706364e-05, "loss": 0.1647, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.3435064373212785, "learning_rate": 2.972118904869376e-05, "loss": 0.1637, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.3340593141915034, "learning_rate": 2.9671725970312563e-05, "loss": 0.1672, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.31684444191613154, "learning_rate": 2.9622185557068238e-05, "loss": 0.1679, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.354616674505305, "learning_rate": 2.95725682050846e-05, "loss": 0.1592, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.288448127838339, "learning_rate": 2.9522874311100684e-05, "loss": 0.1658, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.3015668260207526, "learning_rate": 2.9473104272467526e-05, "loss": 0.1724, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.31715317904119444, "learning_rate": 2.942325848714505e-05, "loss": 0.1718, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.3095675386951616, "learning_rate": 2.9373337353698804e-05, "loss": 0.1722, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.28770233211118934, "learning_rate": 2.932334127129686e-05, "loss": 0.1702, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.30865818082365787, "learning_rate": 2.9273270639706547e-05, "loss": 0.1668, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.310066063188572, "learning_rate": 2.922312585929131e-05, "loss": 0.1604, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.3074769933929992, "learning_rate": 2.9172907331007478e-05, "loss": 0.1619, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.29774587249019446, "learning_rate": 2.9122615456401053e-05, "loss": 0.1618, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.32949882715718926, "learning_rate": 2.9072250637604535e-05, "loss": 0.1649, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3242044248862305, "learning_rate": 2.9021813277333667e-05, "loss": 0.1619, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.365998509723019, "learning_rate": 2.8971303778884244e-05, "loss": 0.1696, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3265138633927836, "learning_rate": 2.8920722546128863e-05, "loss": 0.167, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.33319162549077735, "learning_rate": 2.887006998351372e-05, "loss": 0.1634, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.34019006210307756, "learning_rate": 2.881934649605535e-05, "loss": 0.1664, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.31579319831695973, "learning_rate": 2.8768552489337408e-05, "loss": 0.1697, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.32658158684031413, "learning_rate": 2.8717688369507425e-05, "loss": 0.1745, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.29691860677199383, "learning_rate": 2.8666754543273535e-05, "loss": 0.1677, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.3218197966757533, "learning_rate": 2.8615751417901273e-05, "loss": 0.1725, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.31375731926964656, "learning_rate": 2.856467940121025e-05, "loss": 0.1748, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.28766448126129507, "learning_rate": 2.8513538901570964e-05, "loss": 0.1714, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3236321973338131, "learning_rate": 2.846233032790149e-05, "loss": 0.1718, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.29134408035517045, "learning_rate": 2.84110540896642e-05, "loss": 0.1733, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.2901887079129863, "learning_rate": 2.8359710596862555e-05, "loss": 0.1653, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.31085577536877174, "learning_rate": 2.8308300260037734e-05, "loss": 0.1687, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.28498859629868595, "learning_rate": 2.8256823490265424e-05, "loss": 0.1589, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.301770134675916, "learning_rate": 2.8205280699152515e-05, "loss": 0.1716, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.28634806494569404, "learning_rate": 2.8153672298833777e-05, "loss": 0.1701, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.29773537148766616, "learning_rate": 2.8101998701968615e-05, "loss": 0.1659, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.29030956221788484, "learning_rate": 2.805026032173773e-05, "loss": 0.1673, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3107653345790863, "learning_rate": 2.7998457571839832e-05, "loss": 0.1629, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.32736824594426456, "learning_rate": 2.7946590866488322e-05, "loss": 0.1741, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.2968152814495672, "learning_rate": 2.7894660620408e-05, "loss": 0.1709, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.33319987253918365, "learning_rate": 2.784266724883173e-05, "loss": 0.1721, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.34264911962737155, "learning_rate": 2.7790611167497128e-05, "loss": 0.1625, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3341954575440721, "learning_rate": 2.7738492792643224e-05, "loss": 0.1719, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.33260842228181564, "learning_rate": 2.768631254100716e-05, "loss": 0.1711, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.30831601418966403, "learning_rate": 2.7634070829820836e-05, "loss": 0.1641, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.3334287923672333, "learning_rate": 2.7581768076807592e-05, "loss": 0.1727, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.3212011449004095, "learning_rate": 2.7529404700178832e-05, "loss": 0.1673, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.32206528568714476, "learning_rate": 2.7476981118630735e-05, "loss": 0.1664, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.3443016928789067, "learning_rate": 2.742449775134085e-05, "loss": 0.1753, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.30717118694722495, "learning_rate": 2.7371955017964788e-05, "loss": 0.1775, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.29350589372379315, "learning_rate": 2.7319353338632845e-05, "loss": 0.1727, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3263617312074355, "learning_rate": 2.7266693133946645e-05, "loss": 0.1677, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.2840693131334425, "learning_rate": 2.7213974824975785e-05, "loss": 0.1649, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3172208633336032, "learning_rate": 2.7161198833254464e-05, "loss": 0.1648, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.29819902973325435, "learning_rate": 2.7108365580778095e-05, "loss": 0.1712, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3285503528625473, "learning_rate": 2.705547548999996e-05, "loss": 0.1659, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.28289106574634193, "learning_rate": 2.7002528983827817e-05, "loss": 0.1701, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.2921283894364143, "learning_rate": 2.6949526485620517e-05, "loss": 0.1697, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3194726600074721, "learning_rate": 2.6896468419184623e-05, "loss": 0.1737, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.2815688224045683, "learning_rate": 2.6843355208771024e-05, "loss": 0.167, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.2876618777631377, "learning_rate": 2.6790187279071536e-05, "loss": 0.1668, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.2905725071797009, "learning_rate": 2.67369650552155e-05, "loss": 0.1668, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.33023192966658854, "learning_rate": 2.6683688962766407e-05, "loss": 0.1791, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.2967182936623245, "learning_rate": 2.6630359427718468e-05, "loss": 0.1728, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.33011990449041534, "learning_rate": 2.6576976876493225e-05, "loss": 0.1627, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.31347935874285693, "learning_rate": 2.652354173593614e-05, "loss": 0.1676, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.33583383785785575, "learning_rate": 2.647005443331317e-05, "loss": 0.1699, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.30287340393535184, "learning_rate": 2.6416515396307354e-05, "loss": 0.1646, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3104776068976379, "learning_rate": 2.636292505301542e-05, "loss": 0.1697, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.34426677403157924, "learning_rate": 2.630928383194431e-05, "loss": 0.1701, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.29991686676275703, "learning_rate": 2.625559216200781e-05, "loss": 0.1734, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3060817118946641, "learning_rate": 2.620185047252308e-05, "loss": 0.1724, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.2739175984555455, "learning_rate": 2.614805919320723e-05, "loss": 0.1682, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3399099536251184, "learning_rate": 2.6094218754173895e-05, "loss": 0.1739, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.27089192571534293, "learning_rate": 2.60403295859298e-05, "loss": 0.16, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.32437026014141906, "learning_rate": 2.5986392119371297e-05, "loss": 0.1733, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.2661067198569804, "learning_rate": 2.5932406785780928e-05, "loss": 0.1695, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.32780154855395083, "learning_rate": 2.5878374016823987e-05, "loss": 0.1746, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.30257918016252333, "learning_rate": 2.5824294244545045e-05, "loss": 0.1629, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.2764644222016056, "learning_rate": 2.577016790136453e-05, "loss": 0.17, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.2978552080593239, "learning_rate": 2.5715995420075225e-05, "loss": 0.1672, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.3343799467015306, "learning_rate": 2.5661777233838864e-05, "loss": 0.1692, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.31059512013855733, "learning_rate": 2.5607513776182616e-05, "loss": 0.172, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.30589773611855475, "learning_rate": 2.5553205480995633e-05, "loss": 0.1642, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.3062911320026074, "learning_rate": 2.5498852782525604e-05, "loss": 0.1723, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.2795461088316554, "learning_rate": 2.5444456115375252e-05, "loss": 0.1676, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3121522514322815, "learning_rate": 2.539001591449889e-05, "loss": 0.1662, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.3280819106109578, "learning_rate": 2.53355326151989e-05, "loss": 0.173, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.28207557851122916, "learning_rate": 2.5281006653122288e-05, "loss": 0.1653, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.28763909620837397, "learning_rate": 2.5226438464257217e-05, "loss": 0.171, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3014743568257461, "learning_rate": 2.5171828484929447e-05, "loss": 0.171, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.2563496151309088, "learning_rate": 2.5117177151798934e-05, "loss": 0.1693, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.28350434815872644, "learning_rate": 2.506248490185627e-05, "loss": 0.1685, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.2607376107924269, "learning_rate": 2.500775217241923e-05, "loss": 0.1681, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.27183215596786214, "learning_rate": 2.4952979401129266e-05, "loss": 0.1738, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.27262217422778096, "learning_rate": 2.4898167025948e-05, "loss": 0.1631, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.28913687007789735, "learning_rate": 2.4843315485153703e-05, "loss": 0.1801, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.2735888754830874, "learning_rate": 2.4788425217337856e-05, "loss": 0.1716, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.2936408732816481, "learning_rate": 2.4733496661401572e-05, "loss": 0.1673, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.27078759019248394, "learning_rate": 2.4678530256552114e-05, "loss": 0.1671, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.2819986679401342, "learning_rate": 2.46235264422994e-05, "loss": 0.1695, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.2789332356234931, "learning_rate": 2.4568485658452452e-05, "loss": 0.1786, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.2876052832853665, "learning_rate": 2.451340834511592e-05, "loss": 0.1693, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.2639529436882382, "learning_rate": 2.4458294942686528e-05, "loss": 0.1663, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.30132074409038323, "learning_rate": 2.440314589184958e-05, "loss": 0.1726, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.2969281890425656, "learning_rate": 2.434796163357541e-05, "loss": 0.1736, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.31673146582972506, "learning_rate": 2.429274260911588e-05, "loss": 0.1653, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.27521075128883543, "learning_rate": 2.423748926000084e-05, "loss": 0.1739, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3055562534376384, "learning_rate": 2.418220202803459e-05, "loss": 0.1629, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.2819068294258194, "learning_rate": 2.412688135529237e-05, "loss": 0.1732, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3087329402813728, "learning_rate": 2.4071527684116807e-05, "loss": 0.1664, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.2877179605969684, "learning_rate": 2.4016141457114372e-05, "loss": 0.1698, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.27393481776330225, "learning_rate": 2.396072311715187e-05, "loss": 0.1683, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.2781805583541555, "learning_rate": 2.3905273107352863e-05, "loss": 0.1617, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.2782212632377672, "learning_rate": 2.3849791871094157e-05, "loss": 0.1719, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.27424019335927446, "learning_rate": 2.379427985200223e-05, "loss": 0.1669, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.27102813945245263, "learning_rate": 2.373873749394972e-05, "loss": 0.1725, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.27942098298985396, "learning_rate": 2.3683165241051836e-05, "loss": 0.1612, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.2594229829755935, "learning_rate": 2.3627563537662823e-05, "loss": 0.174, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.3190770862700789, "learning_rate": 2.3571932828372433e-05, "loss": 0.1784, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.2692387706439695, "learning_rate": 2.351627355800233e-05, "loss": 0.1657, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.30197707366987875, "learning_rate": 2.346058617160256e-05, "loss": 0.1687, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.2895213910225167, "learning_rate": 2.3404871114447976e-05, "loss": 0.1699, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.29381162610838807, "learning_rate": 2.334912883203469e-05, "loss": 0.1741, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.2878229106228951, "learning_rate": 2.3293359770076505e-05, "loss": 0.1724, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.2883778088354036, "learning_rate": 2.323756437450136e-05, "loss": 0.1606, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.271239523906583, "learning_rate": 2.3181743091447754e-05, "loss": 0.1681, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.28091372254805635, "learning_rate": 2.3125896367261164e-05, "loss": 0.1713, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.29579772664639425, "learning_rate": 2.307002464849052e-05, "loss": 0.1727, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.27401992286558174, "learning_rate": 2.30141283818846e-05, "loss": 0.1667, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.2900251794321849, "learning_rate": 2.2958208014388462e-05, "loss": 0.1675, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.2676912071919914, "learning_rate": 2.2902263993139857e-05, "loss": 0.1746, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.3084092289017758, "learning_rate": 2.2846296765465708e-05, "loss": 0.171, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.2900006571830386, "learning_rate": 2.2790306778878465e-05, "loss": 0.1716, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.29031704324013546, "learning_rate": 2.273429448107257e-05, "loss": 0.1661, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.2679829204815399, "learning_rate": 2.2678260319920868e-05, "loss": 0.1724, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.2880651509100658, "learning_rate": 2.262220474347102e-05, "loss": 0.1695, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.273773039640097, "learning_rate": 2.2566128199941918e-05, "loss": 0.1685, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.28625943956126815, "learning_rate": 2.2510031137720104e-05, "loss": 0.1636, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.2683068929866562, "learning_rate": 2.2453914005356206e-05, "loss": 0.1701, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.2700377539536406, "learning_rate": 2.2397777251561302e-05, "loss": 0.1682, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.2646459225582654, "learning_rate": 2.2341621325203393e-05, "loss": 0.1685, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.29009333342766075, "learning_rate": 2.2285446675303764e-05, "loss": 0.1677, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.26077513934020385, "learning_rate": 2.2229253751033423e-05, "loss": 0.1671, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.29217382298951666, "learning_rate": 2.2173043001709492e-05, "loss": 0.1666, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.2939749198489803, "learning_rate": 2.2116814876791627e-05, "loss": 0.1707, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.26284362909208214, "learning_rate": 2.2060569825878413e-05, "loss": 0.1711, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.2911882386950029, "learning_rate": 2.2004308298703777e-05, "loss": 0.1646, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.2791474124473754, "learning_rate": 2.1948030745133396e-05, "loss": 0.164, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.30500408993183775, "learning_rate": 2.1891737615161083e-05, "loss": 0.1664, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.2767773019385766, "learning_rate": 2.1835429358905218e-05, "loss": 0.1746, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.2924522166000797, "learning_rate": 2.17791064266051e-05, "loss": 0.1717, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.2711974057288678, "learning_rate": 2.172276926861741e-05, "loss": 0.168, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.28796197380045224, "learning_rate": 2.166641833541255e-05, "loss": 0.1722, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.2935035563215367, "learning_rate": 2.161005407757109e-05, "loss": 0.1649, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.28363572950996574, "learning_rate": 2.155367694578013e-05, "loss": 0.1702, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.268178896260699, "learning_rate": 2.1497287390829712e-05, "loss": 0.1656, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.2715754968379125, "learning_rate": 2.1440885863609208e-05, "loss": 0.1752, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.2700637217862633, "learning_rate": 2.1384472815103737e-05, "loss": 0.1783, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.2712431989800584, "learning_rate": 2.1328048696390534e-05, "loss": 0.1659, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.2809759660757419, "learning_rate": 2.1271613958635342e-05, "loss": 0.1731, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.2586922819544259, "learning_rate": 2.1215169053088825e-05, "loss": 0.1723, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.25657588636098866, "learning_rate": 2.1158714431082937e-05, "loss": 0.1675, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.2682808182255377, "learning_rate": 2.110225054402733e-05, "loss": 0.1682, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.2722953866711019, "learning_rate": 2.1045777843405747e-05, "loss": 0.1788, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.2608893934293782, "learning_rate": 2.09892967807724e-05, "loss": 0.1655, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.28075995223702627, "learning_rate": 2.093280780774835e-05, "loss": 0.1679, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.259575582917249, "learning_rate": 2.087631137601793e-05, "loss": 0.1646, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.32958874945082295, "learning_rate": 2.0819807937325104e-05, "loss": 0.1714, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.3030281973638807, "learning_rate": 2.0763297943469847e-05, "loss": 0.1741, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.2669428863204061, "learning_rate": 2.070678184630458e-05, "loss": 0.1664, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.29765719596592083, "learning_rate": 2.06502600977305e-05, "loss": 0.171, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.289238748345367, "learning_rate": 2.0593733149694008e-05, "loss": 0.1726, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.26830538408227916, "learning_rate": 2.0537201454183074e-05, "loss": 0.1623, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3138195907892302, "learning_rate": 2.0480665463223626e-05, "loss": 0.1679, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.2584977788996118, "learning_rate": 2.042412562887594e-05, "loss": 0.1632, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.30025472837292666, "learning_rate": 2.0367582403231033e-05, "loss": 0.1613, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.31388575991064427, "learning_rate": 2.0311036238407023e-05, "loss": 0.1709, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.2715804788351131, "learning_rate": 2.0254487586545534e-05, "loss": 0.1666, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.30596196202793385, "learning_rate": 2.0197936899808088e-05, "loss": 0.1754, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.2836612578983751, "learning_rate": 2.0141384630372466e-05, "loss": 0.1676, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.3041240126343427, "learning_rate": 2.0084831230429106e-05, "loss": 0.1714, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.29435914223905413, "learning_rate": 2.0028277152177492e-05, "loss": 0.1684, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.333453819784522, "learning_rate": 1.9971722847822518e-05, "loss": 0.1668, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.2760064611922408, "learning_rate": 1.99151687695709e-05, "loss": 0.1722, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2857098510075999, "learning_rate": 1.9858615369627537e-05, "loss": 0.1714, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.29517024164270267, "learning_rate": 1.9802063100191916e-05, "loss": 0.1662, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.2661099938028644, "learning_rate": 1.974551241345447e-05, "loss": 0.1688, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.25705957742586943, "learning_rate": 1.9688963761592984e-05, "loss": 0.1576, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.2593010424870293, "learning_rate": 1.963241759676897e-05, "loss": 0.1629, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.28180902794425866, "learning_rate": 1.9575874371124066e-05, "loss": 0.1602, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.2684901192425952, "learning_rate": 1.951933453677638e-05, "loss": 0.1673, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.28256756106699304, "learning_rate": 1.9462798545816932e-05, "loss": 0.1608, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.2571992107548335, "learning_rate": 1.9406266850305996e-05, "loss": 0.1706, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.2647561738696269, "learning_rate": 1.9349739902269503e-05, "loss": 0.1655, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.29224294016272767, "learning_rate": 1.9293218153695425e-05, "loss": 0.1631, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2591908994036958, "learning_rate": 1.9236702056530153e-05, "loss": 0.1711, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.2694571308800473, "learning_rate": 1.9180192062674907e-05, "loss": 0.1651, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.3009526384468738, "learning_rate": 1.9123688623982076e-05, "loss": 0.1698, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.2828724847411874, "learning_rate": 1.906719219225165e-05, "loss": 0.1623, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.25118684308881345, "learning_rate": 1.9010703219227603e-05, "loss": 0.1765, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.29070556985203905, "learning_rate": 1.8954222156594256e-05, "loss": 0.1699, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.2620044540639848, "learning_rate": 1.8897749455972673e-05, "loss": 0.1712, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.2660085544700064, "learning_rate": 1.884128556891707e-05, "loss": 0.1662, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.25788927064743156, "learning_rate": 1.878483094691119e-05, "loss": 0.1645, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.2704217460824588, "learning_rate": 1.8728386041364664e-05, "loss": 0.1657, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.245174271976665, "learning_rate": 1.867195130360947e-05, "loss": 0.1601, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.290734276372507, "learning_rate": 1.8615527184896263e-05, "loss": 0.1681, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.253299382549841, "learning_rate": 1.8559114136390795e-05, "loss": 0.1637, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.25241696863262775, "learning_rate": 1.8502712609170298e-05, "loss": 0.1617, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.25907251805524284, "learning_rate": 1.8446323054219876e-05, "loss": 0.1664, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.26550794646316017, "learning_rate": 1.838994592242891e-05, "loss": 0.1682, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.2703709680723581, "learning_rate": 1.8333581664587453e-05, "loss": 0.1618, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.2713036149610157, "learning_rate": 1.8277230731382593e-05, "loss": 0.1707, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.2689988869779325, "learning_rate": 1.82208935733949e-05, "loss": 0.1705, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.28842260015015553, "learning_rate": 1.8164570641094793e-05, "loss": 0.1767, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.2834082522781514, "learning_rate": 1.810826238483892e-05, "loss": 0.1632, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.27541121555331083, "learning_rate": 1.8051969254866608e-05, "loss": 0.1679, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.24669630376302387, "learning_rate": 1.7995691701296226e-05, "loss": 0.1688, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.2794438364744104, "learning_rate": 1.7939430174121593e-05, "loss": 0.1687, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.27650970868402497, "learning_rate": 1.788318512320838e-05, "loss": 0.1663, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.2591397300391268, "learning_rate": 1.782695699829051e-05, "loss": 0.1699, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.2925285201352969, "learning_rate": 1.7770746248966587e-05, "loss": 0.1664, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.2429975387125887, "learning_rate": 1.7714553324696243e-05, "loss": 0.1592, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.2446723291069081, "learning_rate": 1.7658378674796614e-05, "loss": 0.1652, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3019728724847952, "learning_rate": 1.76022227484387e-05, "loss": 0.171, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.27195798443572866, "learning_rate": 1.7546085994643807e-05, "loss": 0.1702, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.27936078819097737, "learning_rate": 1.7489968862279902e-05, "loss": 0.1677, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.2645244085478539, "learning_rate": 1.743387180005809e-05, "loss": 0.1703, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.28162982623267463, "learning_rate": 1.737779525652899e-05, "loss": 0.1638, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2731184035693993, "learning_rate": 1.732173968007914e-05, "loss": 0.1641, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2840043109886888, "learning_rate": 1.7265705518927437e-05, "loss": 0.1658, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.2836846696967101, "learning_rate": 1.7209693221121542e-05, "loss": 0.1619, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.24170404750448946, "learning_rate": 1.7153703234534302e-05, "loss": 0.1606, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.2880794939675727, "learning_rate": 1.709773600686015e-05, "loss": 0.1563, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.28174022369232055, "learning_rate": 1.7041791985611548e-05, "loss": 0.1749, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.27176871260055363, "learning_rate": 1.69858716181154e-05, "loss": 0.1705, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.27441189544700256, "learning_rate": 1.692997535150948e-05, "loss": 0.1579, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.2922421041664368, "learning_rate": 1.687410363273884e-05, "loss": 0.1751, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.29128184657789835, "learning_rate": 1.6818256908552257e-05, "loss": 0.1658, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.25373698874271616, "learning_rate": 1.6762435625498646e-05, "loss": 0.1676, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.2773951502680574, "learning_rate": 1.67066402299235e-05, "loss": 0.1635, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.2634560032331455, "learning_rate": 1.6650871167965313e-05, "loss": 0.1641, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.2979112953408395, "learning_rate": 1.6595128885552028e-05, "loss": 0.1673, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.28468615268415387, "learning_rate": 1.653941382839745e-05, "loss": 0.1582, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.2991694237599068, "learning_rate": 1.6483726441997673e-05, "loss": 0.1235, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.30923507975035647, "learning_rate": 1.642806717162757e-05, "loss": 0.1234, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.2683496650283432, "learning_rate": 1.637243646233718e-05, "loss": 0.124, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.3514985038265951, "learning_rate": 1.6316834758948174e-05, "loss": 0.1211, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.3903974393377174, "learning_rate": 1.6261262506050282e-05, "loss": 0.1219, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.29600071320149324, "learning_rate": 1.620572014799777e-05, "loss": 0.1172, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.29084933766847637, "learning_rate": 1.6150208128905857e-05, "loss": 0.1244, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.2968281092576235, "learning_rate": 1.6094726892647147e-05, "loss": 0.1224, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.28311054786615164, "learning_rate": 1.6039276882848135e-05, "loss": 0.1147, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.2902112173027553, "learning_rate": 1.5983858542885635e-05, "loss": 0.1219, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.2862040145082717, "learning_rate": 1.5928472315883203e-05, "loss": 0.1183, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.2913846402611053, "learning_rate": 1.5873118644707633e-05, "loss": 0.1181, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.28647905913238736, "learning_rate": 1.5817797971965413e-05, "loss": 0.1174, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.31372511978395795, "learning_rate": 1.576251073999917e-05, "loss": 0.1185, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.2935438678296584, "learning_rate": 1.5707257390884126e-05, "loss": 0.1209, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.2789294062923176, "learning_rate": 1.5652038366424595e-05, "loss": 0.1194, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.2963734855604963, "learning_rate": 1.5596854108150424e-05, "loss": 0.1171, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.288788368743187, "learning_rate": 1.5541705057313476e-05, "loss": 0.1183, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.2707645378517922, "learning_rate": 1.5486591654884086e-05, "loss": 0.1168, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.2617186737972111, "learning_rate": 1.543151434154755e-05, "loss": 0.1135, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.2691783007514804, "learning_rate": 1.5376473557700615e-05, "loss": 0.1146, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.2826724575747996, "learning_rate": 1.5321469743447893e-05, "loss": 0.1169, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.2852866130596381, "learning_rate": 1.5266503338598434e-05, "loss": 0.1187, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.27684922798557215, "learning_rate": 1.5211574782662149e-05, "loss": 0.1171, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.2704622661418884, "learning_rate": 1.5156684514846307e-05, "loss": 0.111, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.27702938408014655, "learning_rate": 1.5101832974052012e-05, "loss": 0.12, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3092983243643445, "learning_rate": 1.5047020598870737e-05, "loss": 0.1161, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.29117018546281076, "learning_rate": 1.4992247827580778e-05, "loss": 0.1193, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.26165935081212344, "learning_rate": 1.493751509814374e-05, "loss": 0.1159, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.28796335401346984, "learning_rate": 1.4882822848201073e-05, "loss": 0.1167, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.32260695218853425, "learning_rate": 1.4828171515070553e-05, "loss": 0.1168, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2806252476403066, "learning_rate": 1.4773561535742793e-05, "loss": 0.1196, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.29223272894861874, "learning_rate": 1.4718993346877715e-05, "loss": 0.1194, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.28843884301571165, "learning_rate": 1.466446738480111e-05, "loss": 0.1138, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.29776139669129026, "learning_rate": 1.460998408550112e-05, "loss": 0.1178, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.2752792495541877, "learning_rate": 1.4555543884624751e-05, "loss": 0.1116, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.2914795828308118, "learning_rate": 1.4501147217474402e-05, "loss": 0.1141, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.30332059643680814, "learning_rate": 1.444679451900437e-05, "loss": 0.124, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.2788880894044097, "learning_rate": 1.4392486223817397e-05, "loss": 0.1154, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2689002615812521, "learning_rate": 1.4338222766161143e-05, "loss": 0.1142, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2808021134593957, "learning_rate": 1.4284004579924777e-05, "loss": 0.1165, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.2780356040726011, "learning_rate": 1.4229832098635479e-05, "loss": 0.1228, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.2630207342456501, "learning_rate": 1.4175705755454963e-05, "loss": 0.1161, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2950580494817364, "learning_rate": 1.412162598317602e-05, "loss": 0.1179, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.2786954177106121, "learning_rate": 1.406759321421907e-05, "loss": 0.1232, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2718760825435161, "learning_rate": 1.401360788062871e-05, "loss": 0.1158, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.283130079041711, "learning_rate": 1.3959670414070204e-05, "loss": 0.118, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.2803428761711863, "learning_rate": 1.3905781245826108e-05, "loss": 0.1187, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.3036515903937848, "learning_rate": 1.3851940806792778e-05, "loss": 0.1232, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.2806227413478047, "learning_rate": 1.379814952747693e-05, "loss": 0.1204, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2819800040958386, "learning_rate": 1.3744407837992193e-05, "loss": 0.1143, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.3077338435045711, "learning_rate": 1.3690716168055692e-05, "loss": 0.1286, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.2950647468249055, "learning_rate": 1.363707494698459e-05, "loss": 0.1188, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.274018379446738, "learning_rate": 1.358348460369265e-05, "loss": 0.1169, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2694177076136272, "learning_rate": 1.352994556668684e-05, "loss": 0.1159, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3184944141134174, "learning_rate": 1.3476458264063865e-05, "loss": 0.1179, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.2956425389477556, "learning_rate": 1.342302312350678e-05, "loss": 0.1205, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.27705586506161967, "learning_rate": 1.3369640572281537e-05, "loss": 0.1165, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.2812518470221067, "learning_rate": 1.3316311037233596e-05, "loss": 0.1168, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2657816551546206, "learning_rate": 1.326303494478451e-05, "loss": 0.1206, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.27990433508505624, "learning_rate": 1.3209812720928472e-05, "loss": 0.1226, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2786236697701011, "learning_rate": 1.315664479122898e-05, "loss": 0.1221, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.2871608921645914, "learning_rate": 1.3103531580815378e-05, "loss": 0.1201, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.27935454009035754, "learning_rate": 1.3050473514379488e-05, "loss": 0.1225, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2783987383786951, "learning_rate": 1.2997471016172188e-05, "loss": 0.117, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2727829892005306, "learning_rate": 1.2944524510000042e-05, "loss": 0.1205, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2742634518345968, "learning_rate": 1.2891634419221908e-05, "loss": 0.119, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.28802734890586673, "learning_rate": 1.2838801166745545e-05, "loss": 0.1184, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.26913312323796723, "learning_rate": 1.2786025175024216e-05, "loss": 0.121, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.30193465075204906, "learning_rate": 1.2733306866053357e-05, "loss": 0.12, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2872364967383615, "learning_rate": 1.2680646661367163e-05, "loss": 0.1214, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.2751960967299869, "learning_rate": 1.2628044982035219e-05, "loss": 0.1178, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.26704710702276874, "learning_rate": 1.2575502248659155e-05, "loss": 0.1233, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2681362494559006, "learning_rate": 1.2523018881369269e-05, "loss": 0.1163, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.27450932956766716, "learning_rate": 1.2470595299821176e-05, "loss": 0.1195, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.25495585262294634, "learning_rate": 1.2418231923192416e-05, "loss": 0.1187, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.2627996015601388, "learning_rate": 1.2365929170179165e-05, "loss": 0.121, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.2650018535568638, "learning_rate": 1.2313687458992848e-05, "loss": 0.117, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.25753730372529765, "learning_rate": 1.2261507207356785e-05, "loss": 0.1136, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.27042751131687504, "learning_rate": 1.220938883250288e-05, "loss": 0.1177, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.283278979971399, "learning_rate": 1.215733275116827e-05, "loss": 0.1166, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.287382261285095, "learning_rate": 1.2105339379592005e-05, "loss": 0.1186, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.274495401397591, "learning_rate": 1.2053409133511681e-05, "loss": 0.1209, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.2776646203801429, "learning_rate": 1.2001542428160173e-05, "loss": 0.1136, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.27905146457528757, "learning_rate": 1.1949739678262278e-05, "loss": 0.1189, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.26513424231524896, "learning_rate": 1.189800129803139e-05, "loss": 0.1149, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.27587157253187544, "learning_rate": 1.1846327701166228e-05, "loss": 0.1168, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.2733681310969651, "learning_rate": 1.1794719300847493e-05, "loss": 0.1204, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.26381276228408146, "learning_rate": 1.1743176509734582e-05, "loss": 0.1177, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2867267581798051, "learning_rate": 1.1691699739962275e-05, "loss": 0.1209, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.2823590760918717, "learning_rate": 1.1640289403137456e-05, "loss": 0.1222, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.27957375814072544, "learning_rate": 1.1588945910335802e-05, "loss": 0.1188, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.28086455352343015, "learning_rate": 1.1537669672098517e-05, "loss": 0.1184, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.28705312720145826, "learning_rate": 1.1486461098429036e-05, "loss": 0.1196, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.279920060032042, "learning_rate": 1.1435320598789747e-05, "loss": 0.1232, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.26369942602464297, "learning_rate": 1.1384248582098736e-05, "loss": 0.1132, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.30184031366667763, "learning_rate": 1.1333245456726467e-05, "loss": 0.1241, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.28805837674857376, "learning_rate": 1.128231163049258e-05, "loss": 0.1216, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2640081025199964, "learning_rate": 1.123144751066259e-05, "loss": 0.123, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2842698882359955, "learning_rate": 1.1180653503944657e-05, "loss": 0.1173, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.2676152406462665, "learning_rate": 1.1129930016486287e-05, "loss": 0.1111, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2652369596844444, "learning_rate": 1.107927745387114e-05, "loss": 0.1182, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.2840661004773911, "learning_rate": 1.1028696221115766e-05, "loss": 0.1189, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2786553949176906, "learning_rate": 1.0978186722666341e-05, "loss": 0.1145, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.288478408611772, "learning_rate": 1.0927749362395475e-05, "loss": 0.116, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.3180718972863565, "learning_rate": 1.0877384543598954e-05, "loss": 0.1161, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2605119343778385, "learning_rate": 1.0827092668992529e-05, "loss": 0.1153, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2714775540913669, "learning_rate": 1.077687414070869e-05, "loss": 0.1184, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.2805302954271146, "learning_rate": 1.0726729360293451e-05, "loss": 0.1221, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.27537266900450275, "learning_rate": 1.0676658728703147e-05, "loss": 0.1168, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.28282870559574513, "learning_rate": 1.0626662646301198e-05, "loss": 0.1182, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2871255755106994, "learning_rate": 1.0576741512854958e-05, "loss": 0.1181, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2740715758991112, "learning_rate": 1.052689572753247e-05, "loss": 0.1167, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2820664120753114, "learning_rate": 1.0477125688899328e-05, "loss": 0.1213, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.27541252189038706, "learning_rate": 1.0427431794915406e-05, "loss": 0.111, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2874685088142033, "learning_rate": 1.0377814442931769e-05, "loss": 0.1147, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2655786484960237, "learning_rate": 1.0328274029687439e-05, "loss": 0.1155, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.29850419229769926, "learning_rate": 1.0278810951306253e-05, "loss": 0.1225, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.28226229890774673, "learning_rate": 1.0229425603293647e-05, "loss": 0.1196, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.2719915992667991, "learning_rate": 1.0180118380533558e-05, "loss": 0.1245, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2789637608132316, "learning_rate": 1.0130889677285225e-05, "loss": 0.1249, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.2709834428542313, "learning_rate": 1.008173988718005e-05, "loss": 0.116, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2751449712383361, "learning_rate": 1.0032669403218439e-05, "loss": 0.1155, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.28073184619185504, "learning_rate": 9.983678617766677e-06, "loss": 0.1167, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2755809158503606, "learning_rate": 9.934767922553788e-06, "loss": 0.1249, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2870959635055331, "learning_rate": 9.885937708668371e-06, "loss": 0.1165, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.28146465442324786, "learning_rate": 9.837188366555524e-06, "loss": 0.1201, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.27870518241306025, "learning_rate": 9.788520286013691e-06, "loss": 0.1167, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2866545974172463, "learning_rate": 9.739933856191537e-06, "loss": 0.1187, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2752339537906424, "learning_rate": 9.691429465584866e-06, "loss": 0.1157, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.27866152803333494, "learning_rate": 9.643007502033492e-06, "loss": 0.1177, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.28193749192601714, "learning_rate": 9.594668352718152e-06, "loss": 0.1203, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.27158036003014857, "learning_rate": 9.546412404157383e-06, "loss": 0.1174, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.2799832883391606, "learning_rate": 9.498240042204471e-06, "loss": 0.1185, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.297406265941171, "learning_rate": 9.450151652044339e-06, "loss": 0.1197, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2912469983126229, "learning_rate": 9.402147618190472e-06, "loss": 0.1184, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.2807141359663659, "learning_rate": 9.354228324481841e-06, "loss": 0.1227, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.271470363790425, "learning_rate": 9.306394154079852e-06, "loss": 0.1212, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.2788473738553579, "learning_rate": 9.258645489465254e-06, "loss": 0.1162, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.27598701208437476, "learning_rate": 9.21098271243509e-06, "loss": 0.1209, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.273006365834555, "learning_rate": 9.163406204099659e-06, "loss": 0.1159, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.2825703010215371, "learning_rate": 9.115916344879452e-06, "loss": 0.1227, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2664126167273659, "learning_rate": 9.068513514502126e-06, "loss": 0.1144, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.26631289005071246, "learning_rate": 9.021198091999439e-06, "loss": 0.1135, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.2797577721213547, "learning_rate": 8.973970455704251e-06, "loss": 0.115, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.2694395668101127, "learning_rate": 8.926830983247495e-06, "loss": 0.1141, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.27009196524571744, "learning_rate": 8.879780051555116e-06, "loss": 0.12, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2800082413946226, "learning_rate": 8.83281803684512e-06, "loss": 0.1158, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.2716074984517453, "learning_rate": 8.785945314624532e-06, "loss": 0.1159, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.27620752310508784, "learning_rate": 8.739162259686385e-06, "loss": 0.1126, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.26016684870163126, "learning_rate": 8.692469246106734e-06, "loss": 0.116, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.26503987201865326, "learning_rate": 8.645866647241677e-06, "loss": 0.1167, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2722866686515415, "learning_rate": 8.599354835724348e-06, "loss": 0.1111, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2701879029171042, "learning_rate": 8.552934183461958e-06, "loss": 0.1125, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2716427448302256, "learning_rate": 8.506605061632805e-06, "loss": 0.1142, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.2737147483451574, "learning_rate": 8.460367840683308e-06, "loss": 0.1169, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2801419771886544, "learning_rate": 8.414222890325065e-06, "loss": 0.1215, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.286197212232481, "learning_rate": 8.368170579531855e-06, "loss": 0.1139, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.27593345977615225, "learning_rate": 8.322211276536733e-06, "loss": 0.1111, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.2755442504937315, "learning_rate": 8.27634534882907e-06, "loss": 0.1181, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.2903073039253987, "learning_rate": 8.230573163151585e-06, "loss": 0.1143, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.28321725382875435, "learning_rate": 8.184895085497466e-06, "loss": 0.1182, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.26525248671645546, "learning_rate": 8.139311481107401e-06, "loss": 0.1173, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.292185973720496, "learning_rate": 8.093822714466686e-06, "loss": 0.1197, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.29091790712608956, "learning_rate": 8.048429149302271e-06, "loss": 0.1189, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.26391289187142575, "learning_rate": 8.003131148579902e-06, "loss": 0.1172, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2637888385847183, "learning_rate": 7.957929074501182e-06, "loss": 0.1155, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.30964496739950914, "learning_rate": 7.912823288500695e-06, "loss": 0.1182, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.27755336227544364, "learning_rate": 7.867814151243102e-06, "loss": 0.1122, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2653558567162303, "learning_rate": 7.822902022620267e-06, "loss": 0.1093, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.27355815128529704, "learning_rate": 7.778087261748377e-06, "loss": 0.1126, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.2806207628910348, "learning_rate": 7.733370226965056e-06, "loss": 0.1118, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.281673492118214, "learning_rate": 7.688751275826527e-06, "loss": 0.1123, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2631756683561702, "learning_rate": 7.644230765104735e-06, "loss": 0.1133, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.2776200295252151, "learning_rate": 7.599809050784502e-06, "loss": 0.1129, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2934702100055268, "learning_rate": 7.555486488060661e-06, "loss": 0.1193, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2775649524877093, "learning_rate": 7.511263431335249e-06, "loss": 0.1112, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.27892658440697227, "learning_rate": 7.467140234214656e-06, "loss": 0.1235, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.2652318260520278, "learning_rate": 7.423117249506777e-06, "loss": 0.1169, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.2711104376220288, "learning_rate": 7.379194829218231e-06, "loss": 0.1159, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.2845059663281615, "learning_rate": 7.335373324551518e-06, "loss": 0.1182, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.27709395393585917, "learning_rate": 7.291653085902224e-06, "loss": 0.1195, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2724725906311643, "learning_rate": 7.248034462856213e-06, "loss": 0.1178, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2655994683215681, "learning_rate": 7.20451780418683e-06, "loss": 0.113, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2551968781879382, "learning_rate": 7.161103457852128e-06, "loss": 0.1155, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.25436951211257175, "learning_rate": 7.117791770992046e-06, "loss": 0.1147, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.26764499571659384, "learning_rate": 7.074583089925688e-06, "loss": 0.1141, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.2794260774025873, "learning_rate": 7.0314777601485155e-06, "loss": 0.1161, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.2772465992313523, "learning_rate": 6.988476126329604e-06, "loss": 0.1139, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.2825546077516395, "learning_rate": 6.945578532308857e-06, "loss": 0.1172, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.2609261589586036, "learning_rate": 6.902785321094301e-06, "loss": 0.1153, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.28282843860303236, "learning_rate": 6.8600968348593115e-06, "loss": 0.1168, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.25443159963638934, "learning_rate": 6.817513414939892e-06, "loss": 0.1149, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.2819604556195481, "learning_rate": 6.775035401831924e-06, "loss": 0.1128, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.25076269686586083, "learning_rate": 6.732663135188473e-06, "loss": 0.1105, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.2699010205961939, "learning_rate": 6.690396953817055e-06, "loss": 0.1124, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.2516065224135769, "learning_rate": 6.648237195676927e-06, "loss": 0.1183, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.25786262412932803, "learning_rate": 6.606184197876395e-06, "loss": 0.1106, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.26140810960826616, "learning_rate": 6.564238296670109e-06, "loss": 0.1145, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2697004381937278, "learning_rate": 6.52239982745638e-06, "loss": 0.1146, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.2680428255249127, "learning_rate": 6.480669124774484e-06, "loss": 0.1164, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.25420868573319894, "learning_rate": 6.439046522302013e-06, "loss": 0.1138, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.261574030392471, "learning_rate": 6.397532352852191e-06, "loss": 0.116, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.26073489577605335, "learning_rate": 6.356126948371202e-06, "loss": 0.1178, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.28571834356271175, "learning_rate": 6.314830639935559e-06, "loss": 0.1124, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.26909599273828033, "learning_rate": 6.273643757749448e-06, "loss": 0.1201, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.2790100052276959, "learning_rate": 6.2325666311420856e-06, "loss": 0.1172, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2559189330123832, "learning_rate": 6.1915995885650675e-06, "loss": 0.1133, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.2653559870509655, "learning_rate": 6.150742957589784e-06, "loss": 0.1119, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.27537124257078055, "learning_rate": 6.109997064904774e-06, "loss": 0.1175, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2556834980010875, "learning_rate": 6.069362236313092e-06, "loss": 0.1088, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2622271376358033, "learning_rate": 6.0288387967297565e-06, "loss": 0.118, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.267314248604466, "learning_rate": 5.988427070179108e-06, "loss": 0.1129, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2806865809472266, "learning_rate": 5.948127379792234e-06, "loss": 0.1127, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.2726614241295018, "learning_rate": 5.90794004780439e-06, "loss": 0.1158, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.2533067149378475, "learning_rate": 5.867865395552405e-06, "loss": 0.112, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.26548252976931386, "learning_rate": 5.8279037434721364e-06, "loss": 0.1172, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.2578706199040504, "learning_rate": 5.788055411095892e-06, "loss": 0.1167, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.270148832543139, "learning_rate": 5.7483207170498625e-06, "loss": 0.1142, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.2696116207899277, "learning_rate": 5.708699979051613e-06, "loss": 0.1128, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2646671716682535, "learning_rate": 5.66919351390751e-06, "loss": 0.11, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.26336944925039213, "learning_rate": 5.629801637510188e-06, "loss": 0.1104, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.266219165605994, "learning_rate": 5.590524664836043e-06, "loss": 0.1107, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.27225672672106604, "learning_rate": 5.551362909942708e-06, "loss": 0.1169, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.25884257162287827, "learning_rate": 5.51231668596653e-06, "loss": 0.1125, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.26214699423036636, "learning_rate": 5.47338630512007e-06, "loss": 0.1143, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.270352086802047, "learning_rate": 5.434572078689617e-06, "loss": 0.1172, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.2686351156296043, "learning_rate": 5.395874317032694e-06, "loss": 0.1134, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.2606075097150847, "learning_rate": 5.357293329575573e-06, "loss": 0.1162, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2653270751323229, "learning_rate": 5.318829424810797e-06, "loss": 0.1169, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.262561036755365, "learning_rate": 5.280482910294728e-06, "loss": 0.1133, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.2619102251139473, "learning_rate": 5.242254092645078e-06, "loss": 0.1163, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2725700906525784, "learning_rate": 5.2041432775384445e-06, "loss": 0.1141, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.25848102551881125, "learning_rate": 5.166150769707892e-06, "loss": 0.1147, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.2560699634822157, "learning_rate": 5.128276872940503e-06, "loss": 0.1184, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.27141619578017306, "learning_rate": 5.090521890074953e-06, "loss": 0.1122, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2659593983391046, "learning_rate": 5.0528861229990675e-06, "loss": 0.1173, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.2696365622105525, "learning_rate": 5.015369872647442e-06, "loss": 0.1148, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.25380192559954295, "learning_rate": 4.9779734389990195e-06, "loss": 0.1129, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.27612576344577805, "learning_rate": 4.940697121074675e-06, "loss": 0.117, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.25825956204654343, "learning_rate": 4.903541216934864e-06, "loss": 0.1186, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.25538950077637823, "learning_rate": 4.8665060236772e-06, "loss": 0.1127, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2518614554565259, "learning_rate": 4.829591837434102e-06, "loss": 0.1209, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.2629422426696136, "learning_rate": 4.792798953370424e-06, "loss": 0.1152, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.25201327705629073, "learning_rate": 4.756127665681083e-06, "loss": 0.1149, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.27365487198251126, "learning_rate": 4.719578267588725e-06, "loss": 0.1119, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.25498454658464387, "learning_rate": 4.6831510513413525e-06, "loss": 0.1118, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3039639447548155, "learning_rate": 4.6468463082100176e-06, "loss": 0.0817, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.27823318545433023, "learning_rate": 4.610664328486485e-06, "loss": 0.076, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.26230308230959, "learning_rate": 4.5746054014809e-06, "loss": 0.0814, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.2427371522269421, "learning_rate": 4.5386698155194766e-06, "loss": 0.0758, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.26602513025951463, "learning_rate": 4.502857857942204e-06, "loss": 0.0779, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3114566121408929, "learning_rate": 4.467169815100549e-06, "loss": 0.0751, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3263879356189022, "learning_rate": 4.431605972355137e-06, "loss": 0.0741, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.33926586190061114, "learning_rate": 4.396166614073516e-06, "loss": 0.0791, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.3384774122674424, "learning_rate": 4.360852023627846e-06, "loss": 0.0762, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.2878639226100169, "learning_rate": 4.325662483392656e-06, "loss": 0.0757, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2832483110792085, "learning_rate": 4.29059827474257e-06, "loss": 0.0732, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.2764624621166588, "learning_rate": 4.255659678050063e-06, "loss": 0.0722, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.2637551371133965, "learning_rate": 4.22084697268323e-06, "loss": 0.0702, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.2765987840718061, "learning_rate": 4.186160437003535e-06, "loss": 0.0702, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.27224351916265926, "learning_rate": 4.151600348363582e-06, "loss": 0.0725, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.27300284642663963, "learning_rate": 4.11716698310493e-06, "loss": 0.0709, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.2808749673857711, "learning_rate": 4.082860616555848e-06, "loss": 0.0698, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.26667005639531466, "learning_rate": 4.048681523029125e-06, "loss": 0.0748, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2707141826441091, "learning_rate": 4.014629975819882e-06, "loss": 0.0704, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.27972271220028394, "learning_rate": 3.9807062472033855e-06, "loss": 0.0776, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2773497329078689, "learning_rate": 3.94691060843287e-06, "loss": 0.0802, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.28512369080828326, "learning_rate": 3.913243329737353e-06, "loss": 0.0721, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.29229152340800874, "learning_rate": 3.879704680319503e-06, "loss": 0.0691, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2701687044942067, "learning_rate": 3.846294928353471e-06, "loss": 0.0723, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.27542381880404426, "learning_rate": 3.8130143409827345e-06, "loss": 0.0746, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2698119771699529, "learning_rate": 3.7798631843179887e-06, "loss": 0.0731, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2684749307049067, "learning_rate": 3.7468417234349973e-06, "loss": 0.0716, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2544795397937651, "learning_rate": 3.7139502223724823e-06, "loss": 0.0722, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2826691725251498, "learning_rate": 3.6811889441300095e-06, "loss": 0.07, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2526271082308552, "learning_rate": 3.648558150665886e-06, "loss": 0.0707, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.26353671773526716, "learning_rate": 3.616058102895075e-06, "loss": 0.0765, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.26525484263955534, "learning_rate": 3.583689060687079e-06, "loss": 0.0722, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.26103551224244614, "learning_rate": 3.5514512828639023e-06, "loss": 0.0728, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.2803107956313845, "learning_rate": 3.51934502719796e-06, "loss": 0.0719, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.2722545380335184, "learning_rate": 3.4873705504100185e-06, "loss": 0.0725, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.2678444915273578, "learning_rate": 3.4555281081671345e-06, "loss": 0.0695, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.27968360709630913, "learning_rate": 3.4238179550806326e-06, "loss": 0.0746, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.26374048464482297, "learning_rate": 3.3922403447040497e-06, "loss": 0.0739, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.27692117168646685, "learning_rate": 3.3607955295311247e-06, "loss": 0.0737, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2663745894048234, "learning_rate": 3.32948376099375e-06, "loss": 0.0731, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.26433866625817815, "learning_rate": 3.2983052894599976e-06, "loss": 0.0693, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2673092086419044, "learning_rate": 3.2672603642320945e-06, "loss": 0.0695, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2630609988502603, "learning_rate": 3.236349233544438e-06, "loss": 0.0731, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.26384017945985816, "learning_rate": 3.205572144561604e-06, "loss": 0.0696, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.26612490347223833, "learning_rate": 3.174929343376374e-06, "loss": 0.073, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2799266094461158, "learning_rate": 3.1444210750077777e-06, "loss": 0.0732, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2594761403209183, "learning_rate": 3.1140475833991046e-06, "loss": 0.0719, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.2619464332236271, "learning_rate": 3.0838091114159895e-06, "loss": 0.0724, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.276735819264051, "learning_rate": 3.0537059008444524e-06, "loss": 0.069, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.27113647479024167, "learning_rate": 3.0237381923889563e-06, "loss": 0.0809, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.26745335914040996, "learning_rate": 2.9939062256704997e-06, "loss": 0.0679, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.26815180097656394, "learning_rate": 2.964210239224696e-06, "loss": 0.0715, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.26107521321941296, "learning_rate": 2.934650470499869e-06, "loss": 0.069, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2669548484320281, "learning_rate": 2.905227155855128e-06, "loss": 0.073, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.27101301536285133, "learning_rate": 2.875940530558519e-06, "loss": 0.0713, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.25984946064893855, "learning_rate": 2.8467908287851154e-06, "loss": 0.0753, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.263400922447518, "learning_rate": 2.8177782836151603e-06, "loss": 0.069, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2729785381373897, "learning_rate": 2.7889031270321874e-06, "loss": 0.0791, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.26540894974075735, "learning_rate": 2.760165589921184e-06, "loss": 0.074, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.25887805365579053, "learning_rate": 2.7315659020667305e-06, "loss": 0.0729, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2657367690790926, "learning_rate": 2.703104292151164e-06, "loss": 0.0739, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.258335194236009, "learning_rate": 2.6747809877527607e-06, "loss": 0.0699, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.2675116932108501, "learning_rate": 2.6465962153439082e-06, "loss": 0.0709, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.26545176603570747, "learning_rate": 2.618550200289303e-06, "loss": 0.0722, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.27492884746204793, "learning_rate": 2.59064316684412e-06, "loss": 0.0699, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.26259020012237905, "learning_rate": 2.562875338152264e-06, "loss": 0.0684, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.26521711064173775, "learning_rate": 2.5352469362445552e-06, "loss": 0.0784, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2632231733270734, "learning_rate": 2.5077581820369523e-06, "loss": 0.0739, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.27144214487868873, "learning_rate": 2.480409295328803e-06, "loss": 0.0678, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.2705058307226958, "learning_rate": 2.45320049480108e-06, "loss": 0.0671, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.2769916512329342, "learning_rate": 2.4261319980146293e-06, "loss": 0.0732, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.26545178506351835, "learning_rate": 2.399204021408421e-06, "loss": 0.071, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.2672443542299752, "learning_rate": 2.3724167802978395e-06, "loss": 0.07, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.2601494727362542, "learning_rate": 2.3457704888729625e-06, "loss": 0.0714, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.2518293203545017, "learning_rate": 2.3192653601968162e-06, "loss": 0.0731, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.25610077772103734, "learning_rate": 2.2929016062037057e-06, "loss": 0.0698, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.28800772578249806, "learning_rate": 2.2666794376975055e-06, "loss": 0.0736, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.26826197215785286, "learning_rate": 2.24059906434998e-06, "loss": 0.0758, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.25802753207989154, "learning_rate": 2.214660694699091e-06, "loss": 0.072, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.266852881969218, "learning_rate": 2.188864536147355e-06, "loss": 0.0737, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.26958714349732255, "learning_rate": 2.1632107949601757e-06, "loss": 0.0693, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.26235208947821714, "learning_rate": 2.137699676264171e-06, "loss": 0.0738, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.26454198557433034, "learning_rate": 2.1123313840455738e-06, "loss": 0.0672, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.25467464703339493, "learning_rate": 2.08710612114857e-06, "loss": 0.0721, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.27662401142939824, "learning_rate": 2.0620240892736953e-06, "loss": 0.0747, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.28530412458739174, "learning_rate": 2.0370854889762e-06, "loss": 0.0724, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.2747651864781016, "learning_rate": 2.0122905196644726e-06, "loss": 0.0774, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.2752332298671, "learning_rate": 1.987639379598427e-06, "loss": 0.0716, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.25754594578702505, "learning_rate": 1.963132265887919e-06, "loss": 0.073, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.27435954859664075, "learning_rate": 1.9387693744911784e-06, "loss": 0.0717, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.26044002466942817, "learning_rate": 1.9145509002132368e-06, "loss": 0.0755, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.2587164091052392, "learning_rate": 1.8904770367043723e-06, "loss": 0.0685, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.25641636340808605, "learning_rate": 1.8665479764585504e-06, "loss": 0.0686, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.26734111823279183, "learning_rate": 1.8427639108118977e-06, "loss": 0.0737, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2550634422311136, "learning_rate": 1.8191250299411755e-06, "loss": 0.0736, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2657936602397197, "learning_rate": 1.7956315228622446e-06, "loss": 0.0698, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.26375838268060814, "learning_rate": 1.7722835774285553e-06, "loss": 0.07, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.24991639651125042, "learning_rate": 1.7490813803296624e-06, "loss": 0.0721, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2671740894079023, "learning_rate": 1.726025117089718e-06, "loss": 0.0709, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2574144060674449, "learning_rate": 1.70311497206598e-06, "loss": 0.0705, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.27234286256852164, "learning_rate": 1.6803511284473638e-06, "loss": 0.0675, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.28030409209412754, "learning_rate": 1.6577337682529538e-06, "loss": 0.0729, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2814591337085356, "learning_rate": 1.6352630723305617e-06, "loss": 0.0692, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.26470146118875126, "learning_rate": 1.612939220355272e-06, "loss": 0.0673, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.26986771900617473, "learning_rate": 1.5907623908280112e-06, "loss": 0.0708, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.25549211981209446, "learning_rate": 1.568732761074121e-06, "loss": 0.0758, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.2627834555725123, "learning_rate": 1.5468505072419237e-06, "loss": 0.0713, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.258759762867335, "learning_rate": 1.5251158043013448e-06, "loss": 0.0707, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2654492895896214, "learning_rate": 1.5035288260424885e-06, "loss": 0.0713, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.26452088657904843, "learning_rate": 1.4820897450742623e-06, "loss": 0.0703, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2570889063985496, "learning_rate": 1.4607987328229767e-06, "loss": 0.0729, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.26574167410218624, "learning_rate": 1.4396559595310056e-06, "loss": 0.07, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2516287100283293, "learning_rate": 1.4186615942553973e-06, "loss": 0.0724, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2720065615807757, "learning_rate": 1.3978158048665424e-06, "loss": 0.0714, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.25768379975711253, "learning_rate": 1.3771187580468115e-06, "loss": 0.0689, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.26009100231719834, "learning_rate": 1.3565706192892392e-06, "loss": 0.0681, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.27189805994330435, "learning_rate": 1.3361715528961993e-06, "loss": 0.0729, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2722680943883752, "learning_rate": 1.3159217219780817e-06, "loss": 0.0745, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.2673177849446793, "learning_rate": 1.2958212884519949e-06, "loss": 0.0705, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.26709638248826406, "learning_rate": 1.2758704130404675e-06, "loss": 0.0739, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.26001729561971404, "learning_rate": 1.2560692552701738e-06, "loss": 0.0758, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2639602807078227, "learning_rate": 1.2364179734706382e-06, "loss": 0.073, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.26841161588872997, "learning_rate": 1.2169167247729852e-06, "loss": 0.0757, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2592501556920676, "learning_rate": 1.1975656651086864e-06, "loss": 0.0716, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.2500172079350466, "learning_rate": 1.1783649492082926e-06, "loss": 0.0674, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.27713062187247695, "learning_rate": 1.1593147306002183e-06, "loss": 0.0699, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.25820230619881057, "learning_rate": 1.140415161609505e-06, "loss": 0.0678, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2551781505608887, "learning_rate": 1.121666393356604e-06, "loss": 0.0722, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2649777106836048, "learning_rate": 1.1030685757561632e-06, "loss": 0.0676, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2772153431802135, "learning_rate": 1.0846218575158373e-06, "loss": 0.0727, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.25850376342472864, "learning_rate": 1.066326386135097e-06, "loss": 0.0699, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.264532035686166, "learning_rate": 1.0481823079040398e-06, "loss": 0.0695, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.26379735454211367, "learning_rate": 1.0301897679022344e-06, "loss": 0.0707, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.26269323138577305, "learning_rate": 1.0123489099975491e-06, "loss": 0.0685, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2662729488925284, "learning_rate": 9.9465987684501e-07, "loss": 0.0698, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.26843257829327544, "learning_rate": 9.771228098856534e-07, "loss": 0.069, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.2754184875434181, "learning_rate": 9.597378493454013e-07, "loss": 0.0709, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.27120739742810973, "learning_rate": 9.425051342339353e-07, "loss": 0.0696, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.26926569277550544, "learning_rate": 9.254248023435864e-07, "loss": 0.0709, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.2557282706511799, "learning_rate": 9.084969902482288e-07, "loss": 0.068, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.26019570016871235, "learning_rate": 8.917218333021993e-07, "loss": 0.0678, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.26689718995876266, "learning_rate": 8.750994656392109e-07, "loss": 0.0657, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2632205917988009, "learning_rate": 8.58630020171265e-07, "loss": 0.0681, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.27596719321633734, "learning_rate": 8.423136285876099e-07, "loss": 0.0767, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2772108668905388, "learning_rate": 8.26150421353682e-07, "loss": 0.0728, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2634837531510259, "learning_rate": 8.101405277100549e-07, "loss": 0.0721, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.26340407972896496, "learning_rate": 7.942840756714077e-07, "loss": 0.0753, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.27900305614715193, "learning_rate": 7.785811920255093e-07, "loss": 0.0725, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.2746739846249056, "learning_rate": 7.630320023322024e-07, "loss": 0.0706, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.26626787555415166, "learning_rate": 7.476366309223903e-07, "loss": 0.0713, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.2614370870511331, "learning_rate": 7.323952008970537e-07, "loss": 0.0673, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2597172430571772, "learning_rate": 7.173078341262618e-07, "loss": 0.0712, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2511516382342733, "learning_rate": 7.023746512481989e-07, "loss": 0.0722, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2591526004981303, "learning_rate": 6.875957716681902e-07, "loss": 0.0736, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.2582105650326176, "learning_rate": 6.729713135577687e-07, "loss": 0.0665, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.26073352141825995, "learning_rate": 6.585013938537143e-07, "loss": 0.0707, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.24889255726967408, "learning_rate": 6.441861282571115e-07, "loss": 0.076, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.26053509167554106, "learning_rate": 6.300256312324471e-07, "loss": 0.0691, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2705729474121634, "learning_rate": 6.160200160066776e-07, "loss": 0.0695, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.25449295183478604, "learning_rate": 6.021693945683327e-07, "loss": 0.0692, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.25029159870499423, "learning_rate": 5.884738776666044e-07, "loss": 0.0681, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.2585159523532712, "learning_rate": 5.749335748104878e-07, "loss": 0.0706, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.26642526640362685, "learning_rate": 5.615485942678778e-07, "loss": 0.0709, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.27122973160326314, "learning_rate": 5.483190430647289e-07, "loss": 0.0693, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.252878883632246, "learning_rate": 5.352450269841747e-07, "loss": 0.0699, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.2616857625609953, "learning_rate": 5.22326650565701e-07, "loss": 0.0743, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2590833789516288, "learning_rate": 5.095640171043048e-07, "loss": 0.0725, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.26691183254297796, "learning_rate": 4.969572286496594e-07, "loss": 0.0686, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.26124094266139514, "learning_rate": 4.845063860053079e-07, "loss": 0.0695, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2550931716225871, "learning_rate": 4.7221158872785997e-07, "loss": 0.0686, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.25320666461347563, "learning_rate": 4.600729351261857e-07, "loss": 0.0693, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.2475063658735737, "learning_rate": 4.4809052226063355e-07, "loss": 0.0715, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.26561617901149764, "learning_rate": 4.3626444594226046e-07, "loss": 0.0686, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.269797317943064, "learning_rate": 4.245948007320588e-07, "loss": 0.068, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.25985557909488327, "learning_rate": 4.130816799401971e-07, "loss": 0.0678, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.25628406525337255, "learning_rate": 4.017251756252827e-07, "loss": 0.0673, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.27800750288182574, "learning_rate": 3.9052537859362473e-07, "loss": 0.0696, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2615166576975719, "learning_rate": 3.7948237839849687e-07, "loss": 0.0777, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.2647672293801468, "learning_rate": 3.6859626333943797e-07, "loss": 0.0705, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.26271006179330203, "learning_rate": 3.578671204615347e-07, "loss": 0.0689, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.2596883956435972, "learning_rate": 3.472950355547267e-07, "loss": 0.0708, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.2620907163805454, "learning_rate": 3.3688009315312244e-07, "loss": 0.0671, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.25154296610912175, "learning_rate": 3.266223765343224e-07, "loss": 0.0687, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.24786125835961756, "learning_rate": 3.16521967718757e-07, "loss": 0.0668, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.26747060757288815, "learning_rate": 3.0657894746902726e-07, "loss": 0.0661, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.24782137874237764, "learning_rate": 2.9679339528925654e-07, "loss": 0.0691, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.2601486029407974, "learning_rate": 2.871653894244597e-07, "loss": 0.0687, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2558937694507294, "learning_rate": 2.7769500685991266e-07, "loss": 0.0693, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2650747255068406, "learning_rate": 2.683823233205485e-07, "loss": 0.0749, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.2656782675252982, "learning_rate": 2.592274132703287e-07, "loss": 0.0702, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.25658719115278583, "learning_rate": 2.502303499116754e-07, "loss": 0.0677, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.26610454814311985, "learning_rate": 2.413912051848666e-07, "loss": 0.0724, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.2638505562080926, "learning_rate": 2.3271004976746613e-07, "loss": 0.0676, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2542299086966235, "learning_rate": 2.2418695307376393e-07, "loss": 0.066, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2523700559127793, "learning_rate": 2.1582198325420968e-07, "loss": 0.0661, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.2679129158676595, "learning_rate": 2.0761520719488447e-07, "loss": 0.0722, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.24705679845911405, "learning_rate": 1.9956669051694798e-07, "loss": 0.0679, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.25706333531770853, "learning_rate": 1.916764975761254e-07, "loss": 0.0699, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2564433793825977, "learning_rate": 1.839446914621923e-07, "loss": 0.0721, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.2526212289195384, "learning_rate": 1.7637133399845962e-07, "loss": 0.0665, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.2622438577496522, "learning_rate": 1.6895648574129397e-07, "loss": 0.0722, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2588967906366285, "learning_rate": 1.6170020597962465e-07, "loss": 0.0656, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.26272038468003267, "learning_rate": 1.5460255273447078e-07, "loss": 0.0701, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.2713863360160369, "learning_rate": 1.4766358275847715e-07, "loss": 0.0727, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.2886715409537431, "learning_rate": 1.4088335153546573e-07, "loss": 0.0702, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.2554487256261794, "learning_rate": 1.3426191327998496e-07, "loss": 0.0699, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.25091680145940914, "learning_rate": 1.277993209368744e-07, "loss": 0.07, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.2625891887343956, "learning_rate": 1.214956261808542e-07, "loss": 0.0719, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.26507420705359175, "learning_rate": 1.1535087941609846e-07, "loss": 0.0727, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.2609954727359366, "learning_rate": 1.0936512977583802e-07, "loss": 0.0705, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.25966934826860083, "learning_rate": 1.0353842512196732e-07, "loss": 0.0691, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.2691742950452656, "learning_rate": 9.787081204466253e-08, "loss": 0.0704, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2693280425814568, "learning_rate": 9.236233586200627e-08, "loss": 0.0712, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2627142881827017, "learning_rate": 8.70130406196279e-08, "loss": 0.0666, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2655260828909827, "learning_rate": 8.182296909035047e-08, "loss": 0.0723, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.25672669588755387, "learning_rate": 7.679216277384439e-08, "loss": 0.0722, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2686761262691237, "learning_rate": 7.19206618963053e-08, "loss": 0.0689, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.25643973797340736, "learning_rate": 6.720850541012347e-08, "loss": 0.0696, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.25652679781184023, "learning_rate": 6.265573099357714e-08, "loss": 0.0657, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.25111394017718225, "learning_rate": 5.826237505053067e-08, "loss": 0.068, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.2599409703205577, "learning_rate": 5.4028472710137e-08, "loss": 0.071, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.27216821176208233, "learning_rate": 4.9954057826571146e-08, "loss": 0.0674, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2693801928880128, "learning_rate": 4.6039162978743776e-08, "loss": 0.0712, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.2653973586743499, "learning_rate": 4.228381947004812e-08, "loss": 0.0654, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.26741740676199016, "learning_rate": 3.868805732811343e-08, "loss": 0.0714, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.25615175108662325, "learning_rate": 3.525190530455636e-08, "loss": 0.069, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.2565150700353402, "learning_rate": 3.197539087475887e-08, "loss": 0.0691, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.27100576214736966, "learning_rate": 2.8858540237641786e-08, "loss": 0.0666, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.26368889866323203, "learning_rate": 2.5901378315458247e-08, "loss": 0.0697, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.25923382305345033, "learning_rate": 2.3103928753598347e-08, "loss": 0.0693, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.26525662783720183, "learning_rate": 2.0466213920393718e-08, "loss": 0.0681, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.2656631407166852, "learning_rate": 1.7988254906942115e-08, "loss": 0.0689, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.2550556867309288, "learning_rate": 1.5670071526936447e-08, "loss": 0.0735, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2591575049961894, "learning_rate": 1.3511682316509344e-08, "loss": 0.0683, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.2867989174768104, "learning_rate": 1.1513104534086605e-08, "loss": 0.0727, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.2637772176964214, "learning_rate": 9.67435416023843e-09, "loss": 0.0721, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.27111765715025926, "learning_rate": 7.995445897566178e-09, "loss": 0.0698, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.26517585381744974, "learning_rate": 6.476393170578021e-09, "loss": 0.0724, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.26130291154551716, "learning_rate": 5.11720812557348e-09, "loss": 0.0655, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.26149460908590616, "learning_rate": 3.917901630563492e-09, "loss": 0.0663, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2567564291427995, "learning_rate": 2.878483275170485e-09, "loss": 0.0718, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.25966233476475536, "learning_rate": 1.998961370555108e-09, "loss": 0.0697, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.265646785236791, "learning_rate": 1.2793429493518361e-09, "loss": 0.0706, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2712033720304931, "learning_rate": 7.196337656112384e-10, "loss": 0.0732, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.2654917920400053, "learning_rate": 3.198382947511292e-10, "loss": 0.0704, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.25443276709793966, "learning_rate": 7.995973352770137e-11, "loss": 0.0758, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.24957980381264172, "learning_rate": 0.0, "loss": 0.0698, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 571694257733632.0, "train_loss": 0.17307198386081318, "train_runtime": 7778.9513, "train_samples_per_second": 20.311, "train_steps_per_second": 0.159 } ], "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": 571694257733632.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }