{ "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": 5.745317266405834, "learning_rate": 3.2258064516129035e-07, "loss": 0.886, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 5.430941484616687, "learning_rate": 6.451612903225807e-07, "loss": 0.908, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 5.290032078917498, "learning_rate": 9.67741935483871e-07, "loss": 0.8705, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 5.070100810731004, "learning_rate": 1.2903225806451614e-06, "loss": 0.8507, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 5.156396778522463, "learning_rate": 1.6129032258064516e-06, "loss": 0.9455, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 4.778052425172734, "learning_rate": 1.935483870967742e-06, "loss": 0.8773, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 3.7840584435044198, "learning_rate": 2.2580645161290324e-06, "loss": 0.8314, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 3.76922537984957, "learning_rate": 2.580645161290323e-06, "loss": 0.9172, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.453959662615861, "learning_rate": 2.903225806451613e-06, "loss": 0.8337, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.1453491053306584, "learning_rate": 3.225806451612903e-06, "loss": 0.8114, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.31082995759485, "learning_rate": 3.548387096774194e-06, "loss": 0.7585, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 2.0536405576011094, "learning_rate": 3.870967741935484e-06, "loss": 0.7743, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 2.131326676453475, "learning_rate": 4.193548387096774e-06, "loss": 0.7808, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 2.5810206906809734, "learning_rate": 4.516129032258065e-06, "loss": 0.8009, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 2.453320650204596, "learning_rate": 4.838709677419355e-06, "loss": 0.9664, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 1.7959830785706368, "learning_rate": 5.161290322580646e-06, "loss": 0.6839, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.2728954357505686, "learning_rate": 5.483870967741935e-06, "loss": 0.7851, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.1125529596499377, "learning_rate": 5.806451612903226e-06, "loss": 0.7486, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.75315080684495, "learning_rate": 6.129032258064517e-06, "loss": 0.7077, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.6095534874717183, "learning_rate": 6.451612903225806e-06, "loss": 0.813, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.3748967388817084, "learning_rate": 6.774193548387097e-06, "loss": 0.7119, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.3885276485973075, "learning_rate": 7.096774193548388e-06, "loss": 0.6717, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.3387499535633482, "learning_rate": 7.4193548387096784e-06, "loss": 0.7419, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.297421172044944, "learning_rate": 7.741935483870968e-06, "loss": 0.6971, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.2650683680124462, "learning_rate": 8.064516129032258e-06, "loss": 0.7208, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.0950621855371774, "learning_rate": 8.387096774193549e-06, "loss": 0.6337, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.0241396814111308, "learning_rate": 8.70967741935484e-06, "loss": 0.6469, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.2515499906586338, "learning_rate": 9.03225806451613e-06, "loss": 0.6725, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.0136278907415366, "learning_rate": 9.35483870967742e-06, "loss": 0.5912, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.1310991970991675, "learning_rate": 9.67741935483871e-06, "loss": 0.68, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 1.2182067168862294, "learning_rate": 1e-05, "loss": 0.6359, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 1.0284177844669862, "learning_rate": 1.0322580645161291e-05, "loss": 0.6047, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 1.1717340530183908, "learning_rate": 1.0645161290322582e-05, "loss": 0.6594, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.9752949612412032, "learning_rate": 1.096774193548387e-05, "loss": 0.6296, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.9727615210090441, "learning_rate": 1.1290322580645164e-05, "loss": 0.655, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.9189426250138102, "learning_rate": 1.1612903225806453e-05, "loss": 0.63, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.8574961302826536, "learning_rate": 1.1935483870967743e-05, "loss": 0.6541, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.9406396098035588, "learning_rate": 1.2258064516129034e-05, "loss": 0.6472, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.8709260498614062, "learning_rate": 1.2580645161290324e-05, "loss": 0.6075, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.8923676693533019, "learning_rate": 1.2903225806451613e-05, "loss": 0.6559, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.8352050203495014, "learning_rate": 1.3225806451612903e-05, "loss": 0.6109, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.7736688829653182, "learning_rate": 1.3548387096774194e-05, "loss": 0.6485, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.9788246577876529, "learning_rate": 1.3870967741935486e-05, "loss": 0.5853, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.8235642435958783, "learning_rate": 1.4193548387096776e-05, "loss": 0.5968, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.7587461896585105, "learning_rate": 1.4516129032258066e-05, "loss": 0.6045, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.7595908284260059, "learning_rate": 1.4838709677419357e-05, "loss": 0.6234, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.7275505437908695, "learning_rate": 1.5161290322580646e-05, "loss": 0.6024, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.7684991043077597, "learning_rate": 1.5483870967741936e-05, "loss": 0.6378, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.7408979236302095, "learning_rate": 1.5806451612903226e-05, "loss": 0.6012, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.9134041662965023, "learning_rate": 1.6129032258064517e-05, "loss": 0.6764, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.8554969556777777, "learning_rate": 1.6451612903225807e-05, "loss": 0.6105, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.8156819312203387, "learning_rate": 1.6774193548387098e-05, "loss": 0.6424, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.9222024305667879, "learning_rate": 1.7096774193548388e-05, "loss": 0.5862, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.754650009518192, "learning_rate": 1.741935483870968e-05, "loss": 0.5742, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.863588330173798, "learning_rate": 1.774193548387097e-05, "loss": 0.6843, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.8607339659869212, "learning_rate": 1.806451612903226e-05, "loss": 0.671, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.8755516452750284, "learning_rate": 1.838709677419355e-05, "loss": 0.6399, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.9521830670414109, "learning_rate": 1.870967741935484e-05, "loss": 0.6418, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.8039412844737561, "learning_rate": 1.903225806451613e-05, "loss": 0.5827, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.8907733244895978, "learning_rate": 1.935483870967742e-05, "loss": 0.6689, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.8746828719001875, "learning_rate": 1.967741935483871e-05, "loss": 0.672, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.8476935890448729, "learning_rate": 2e-05, "loss": 0.5855, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.7384432673446963, "learning_rate": 2.0322580645161292e-05, "loss": 0.7622, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7725262960127725, "learning_rate": 2.0645161290322582e-05, "loss": 0.6125, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.7649865393840821, "learning_rate": 2.0967741935483873e-05, "loss": 0.5952, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.9683683086390349, "learning_rate": 2.1290322580645163e-05, "loss": 0.5782, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7980398065860138, "learning_rate": 2.161290322580645e-05, "loss": 0.6136, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.7844762088303308, "learning_rate": 2.193548387096774e-05, "loss": 0.599, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.9320901933606128, "learning_rate": 2.225806451612903e-05, "loss": 0.6251, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.9478900821134327, "learning_rate": 2.2580645161290328e-05, "loss": 0.6175, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.8663353005956606, "learning_rate": 2.2903225806451615e-05, "loss": 0.6106, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7941953922452957, "learning_rate": 2.3225806451612906e-05, "loss": 0.5842, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.8116178557842268, "learning_rate": 2.3548387096774196e-05, "loss": 0.6286, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.8276823853082892, "learning_rate": 2.3870967741935486e-05, "loss": 0.6392, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.8651017898651445, "learning_rate": 2.4193548387096777e-05, "loss": 0.5719, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.710363211854016, "learning_rate": 2.4516129032258067e-05, "loss": 0.5451, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.8759925778676189, "learning_rate": 2.4838709677419358e-05, "loss": 0.5911, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.8340970441067428, "learning_rate": 2.5161290322580648e-05, "loss": 0.5901, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7796539818919441, "learning_rate": 2.548387096774194e-05, "loss": 0.5656, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.8805094311153078, "learning_rate": 2.5806451612903226e-05, "loss": 0.6606, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.8239358016661977, "learning_rate": 2.6129032258064516e-05, "loss": 0.5962, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.7846827410544318, "learning_rate": 2.6451612903225806e-05, "loss": 0.5572, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8517300224533143, "learning_rate": 2.6774193548387097e-05, "loss": 0.6392, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.9239475160244356, "learning_rate": 2.7096774193548387e-05, "loss": 0.5858, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.7569043970154238, "learning_rate": 2.7419354838709678e-05, "loss": 0.5519, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.912668905654298, "learning_rate": 2.774193548387097e-05, "loss": 0.5767, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.8597734175175585, "learning_rate": 2.8064516129032262e-05, "loss": 0.5782, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.9943484147486512, "learning_rate": 2.8387096774193552e-05, "loss": 0.6393, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.841765280428487, "learning_rate": 2.8709677419354843e-05, "loss": 0.5875, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7580201655328075, "learning_rate": 2.9032258064516133e-05, "loss": 0.7162, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.8774758669904974, "learning_rate": 2.9354838709677423e-05, "loss": 0.6354, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.842621952551189, "learning_rate": 2.9677419354838714e-05, "loss": 0.6257, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.8577022449697599, "learning_rate": 3.0000000000000004e-05, "loss": 0.6552, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7997578778147945, "learning_rate": 3.032258064516129e-05, "loss": 0.5639, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.8357109979167011, "learning_rate": 3.0645161290322585e-05, "loss": 0.7966, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.7579248718273209, "learning_rate": 3.096774193548387e-05, "loss": 0.6089, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.8777138415742552, "learning_rate": 3.1290322580645166e-05, "loss": 0.6046, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.8298962362201198, "learning_rate": 3.161290322580645e-05, "loss": 0.6121, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.9562651123567057, "learning_rate": 3.193548387096774e-05, "loss": 0.599, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.7901382516662755, "learning_rate": 3.2258064516129034e-05, "loss": 0.5741, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.8269043394828142, "learning_rate": 3.258064516129033e-05, "loss": 0.5977, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.9041300686178391, "learning_rate": 3.2903225806451614e-05, "loss": 0.591, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.834441294386908, "learning_rate": 3.322580645161291e-05, "loss": 0.607, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.9562549047279203, "learning_rate": 3.3548387096774195e-05, "loss": 0.783, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.0070506360404814, "learning_rate": 3.387096774193549e-05, "loss": 0.6454, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.8464276009332719, "learning_rate": 3.4193548387096776e-05, "loss": 0.5807, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.793835832323591, "learning_rate": 3.451612903225807e-05, "loss": 0.5787, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.9144376516804352, "learning_rate": 3.483870967741936e-05, "loss": 0.603, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.8401248447177866, "learning_rate": 3.516129032258065e-05, "loss": 0.6356, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.9520151372380875, "learning_rate": 3.548387096774194e-05, "loss": 0.591, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.7949763069482935, "learning_rate": 3.5806451612903225e-05, "loss": 0.6526, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8005796896235753, "learning_rate": 3.612903225806452e-05, "loss": 0.6372, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.7856914452630892, "learning_rate": 3.6451612903225805e-05, "loss": 0.7619, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.8198708744565066, "learning_rate": 3.67741935483871e-05, "loss": 0.6059, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.840456537037105, "learning_rate": 3.7096774193548386e-05, "loss": 0.6351, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.7878317762437375, "learning_rate": 3.741935483870968e-05, "loss": 0.6322, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.6905897510219271, "learning_rate": 3.7741935483870974e-05, "loss": 0.5629, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.6847116652485465, "learning_rate": 3.806451612903226e-05, "loss": 0.584, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.7288744152880996, "learning_rate": 3.8387096774193555e-05, "loss": 0.6127, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.7390293791828924, "learning_rate": 3.870967741935484e-05, "loss": 0.6371, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.7633550132176601, "learning_rate": 3.9032258064516135e-05, "loss": 0.6437, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6290267751799522, "learning_rate": 3.935483870967742e-05, "loss": 0.5966, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7624999552066746, "learning_rate": 3.9677419354838716e-05, "loss": 0.8281, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7276678772755726, "learning_rate": 4e-05, "loss": 0.6054, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.7469596326019524, "learning_rate": 3.9999920040266474e-05, "loss": 0.621, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.6929658373442743, "learning_rate": 3.999968016170525e-05, "loss": 0.588, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.6999739489552095, "learning_rate": 3.9999280366234394e-05, "loss": 0.5833, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.7742750334586328, "learning_rate": 3.999872065705065e-05, "loss": 0.5954, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.7180081831255304, "learning_rate": 3.999800103862945e-05, "loss": 0.6532, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.7357563140818048, "learning_rate": 3.9997121516724834e-05, "loss": 0.5881, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.7130140113389734, "learning_rate": 3.999608209836944e-05, "loss": 0.6106, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.7734824300682208, "learning_rate": 3.999488279187443e-05, "loss": 0.5805, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.7436115460995542, "learning_rate": 3.9993523606829425e-05, "loss": 0.6346, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.8602264906621602, "learning_rate": 3.9992004554102435e-05, "loss": 0.6283, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7985519081615386, "learning_rate": 3.999032564583976e-05, "loss": 0.6522, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.8102058218398756, "learning_rate": 3.998848689546591e-05, "loss": 0.6235, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7433666045855472, "learning_rate": 3.9986488317683496e-05, "loss": 0.6046, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.8367586084560098, "learning_rate": 3.9984329928473067e-05, "loss": 0.6503, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.7783208495929579, "learning_rate": 3.998201174509306e-05, "loss": 0.6261, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.7444024807139771, "learning_rate": 3.997953378607961e-05, "loss": 0.5779, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.8044415860938885, "learning_rate": 3.9976896071246403e-05, "loss": 0.6189, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.7977261047131615, "learning_rate": 3.997409862168454e-05, "loss": 0.5957, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.010610289868071, "learning_rate": 3.997114145976237e-05, "loss": 0.721, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.7716368632387243, "learning_rate": 3.9968024609125245e-05, "loss": 0.5886, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7802480327866538, "learning_rate": 3.996474809469545e-05, "loss": 0.6256, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.7213778065597889, "learning_rate": 3.996131194267189e-05, "loss": 0.6048, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.8150601178088843, "learning_rate": 3.995771618052995e-05, "loss": 0.6315, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.7201335376837915, "learning_rate": 3.9953960837021256e-05, "loss": 0.6049, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7792295962764265, "learning_rate": 3.995004594217343e-05, "loss": 0.677, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6695246215513283, "learning_rate": 3.994597152728987e-05, "loss": 0.5898, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.750134729179582, "learning_rate": 3.994173762494947e-05, "loss": 0.5744, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.7160735881516895, "learning_rate": 3.9937344269006424e-05, "loss": 0.5883, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7843586892123863, "learning_rate": 3.993279149458988e-05, "loss": 0.638, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.6600057983289929, "learning_rate": 3.9928079338103695e-05, "loss": 0.5777, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.6547404149765514, "learning_rate": 3.992320783722616e-05, "loss": 0.6056, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7325853290033105, "learning_rate": 3.991817703090965e-05, "loss": 0.5973, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.7636020592797078, "learning_rate": 3.991298695938038e-05, "loss": 0.6258, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6546837186569076, "learning_rate": 3.9907637664138e-05, "loss": 0.6057, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6855066866439594, "learning_rate": 3.990212918795534e-05, "loss": 0.5729, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.7941716315897918, "learning_rate": 3.9896461574878036e-05, "loss": 0.6309, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6747105412334761, "learning_rate": 3.989063487022416e-05, "loss": 0.6245, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.7002389957020715, "learning_rate": 3.9884649120583903e-05, "loss": 0.7413, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.662132244505383, "learning_rate": 3.987850437381915e-05, "loss": 0.6374, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.7442534017107462, "learning_rate": 3.987220067906313e-05, "loss": 0.6372, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.7733732934073775, "learning_rate": 3.986573808672002e-05, "loss": 0.6304, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6976934076356041, "learning_rate": 3.9859116648464534e-05, "loss": 0.6303, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.7284520299075171, "learning_rate": 3.985233641724152e-05, "loss": 0.6235, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7604005817141165, "learning_rate": 3.984539744726554e-05, "loss": 0.6244, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6800389431951914, "learning_rate": 3.983829979402038e-05, "loss": 0.6173, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.6810606784061612, "learning_rate": 3.983104351425871e-05, "loss": 0.6183, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7218954424048661, "learning_rate": 3.982362866600154e-05, "loss": 0.6131, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6007370302655168, "learning_rate": 3.9816055308537806e-05, "loss": 0.5645, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.7178772697435106, "learning_rate": 3.980832350242388e-05, "loss": 0.6184, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.7433133344333217, "learning_rate": 3.980043330948306e-05, "loss": 0.6283, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.6620711091522538, "learning_rate": 3.9792384792805124e-05, "loss": 0.6113, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.7384161534884605, "learning_rate": 3.978417801674579e-05, "loss": 0.6882, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.6296699131269888, "learning_rate": 3.9775813046926244e-05, "loss": 0.5962, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6372627401367087, "learning_rate": 3.976728995023254e-05, "loss": 0.5776, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6503097032162765, "learning_rate": 3.975860879481514e-05, "loss": 0.6117, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.6456011654591236, "learning_rate": 3.974976965008833e-05, "loss": 0.6321, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.7269692952237724, "learning_rate": 3.9740772586729674e-05, "loss": 0.6075, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.6462530782993512, "learning_rate": 3.973161767667946e-05, "loss": 0.5787, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6769074429586623, "learning_rate": 3.972230499314009e-05, "loss": 0.6454, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.6907115006462472, "learning_rate": 3.9712834610575545e-05, "loss": 0.6013, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.6498179823401833, "learning_rate": 3.9703206604710746e-05, "loss": 0.5733, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.585128314509644, "learning_rate": 3.969342105253098e-05, "loss": 0.5637, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6263658675367583, "learning_rate": 3.9683478032281246e-05, "loss": 0.5918, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.7579819182214638, "learning_rate": 3.967337762346568e-05, "loss": 0.6282, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.5684174880050996, "learning_rate": 3.9663119906846885e-05, "loss": 0.5773, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.6299784842254094, "learning_rate": 3.965270496444528e-05, "loss": 0.6359, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.7464519200144094, "learning_rate": 3.9642132879538465e-05, "loss": 0.6153, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.6535233296160088, "learning_rate": 3.9631403736660566e-05, "loss": 0.6401, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.6651672159758402, "learning_rate": 3.962051762160151e-05, "loss": 0.6305, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.6357122620227567, "learning_rate": 3.960947462140638e-05, "loss": 0.5967, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.7414876313155744, "learning_rate": 3.959827482437472e-05, "loss": 0.6055, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.6453237576815886, "learning_rate": 3.958691832005981e-05, "loss": 0.6161, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.675877545091809, "learning_rate": 3.9575405199267944e-05, "loss": 0.6092, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.7201378215506161, "learning_rate": 3.956373555405774e-05, "loss": 0.6589, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6996867672740892, "learning_rate": 3.955190947773937e-05, "loss": 0.6406, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.6688644040360738, "learning_rate": 3.9539927064873824e-05, "loss": 0.5912, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6925240292483832, "learning_rate": 3.952778841127214e-05, "loss": 0.6125, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.7284173964350927, "learning_rate": 3.95154936139947e-05, "loss": 0.6213, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.8195697879747269, "learning_rate": 3.950304277135034e-05, "loss": 0.6566, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.6806883148874666, "learning_rate": 3.94904359828957e-05, "loss": 0.6813, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.6907716504135184, "learning_rate": 3.94776733494343e-05, "loss": 0.6524, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.6238868010470666, "learning_rate": 3.9464754973015826e-05, "loss": 0.577, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.6592809521726252, "learning_rate": 3.9451680956935275e-05, "loss": 0.5597, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.7638331250552703, "learning_rate": 3.943845140573213e-05, "loss": 0.6139, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.74266251077073, "learning_rate": 3.942506642518952e-05, "loss": 0.6225, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.7458533026745346, "learning_rate": 3.9411526122333396e-05, "loss": 0.6726, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.6824204480628259, "learning_rate": 3.939783060543167e-05, "loss": 0.6366, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.6821625340467273, "learning_rate": 3.938397998399333e-05, "loss": 0.6462, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.7036338466427607, "learning_rate": 3.936997436876756e-05, "loss": 0.5973, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6565186789661632, "learning_rate": 3.935581387174289e-05, "loss": 0.6098, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.7013446352000468, "learning_rate": 3.9341498606146295e-05, "loss": 0.5993, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.6335224103212557, "learning_rate": 3.932702868644224e-05, "loss": 0.6394, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.7440965835321042, "learning_rate": 3.931240422833181e-05, "loss": 0.6149, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7248818461268135, "learning_rate": 3.9297625348751806e-05, "loss": 0.6159, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.6724992984822015, "learning_rate": 3.9282692165873744e-05, "loss": 0.6336, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.6686178805290705, "learning_rate": 3.9267604799102945e-05, "loss": 0.5736, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.6673965874913272, "learning_rate": 3.9252363369077615e-05, "loss": 0.6467, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.7167932851217983, "learning_rate": 3.9236967997667796e-05, "loss": 0.6816, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.6611881522153018, "learning_rate": 3.9221418807974496e-05, "loss": 0.5975, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.7304737105454836, "learning_rate": 3.92057159243286e-05, "loss": 0.6098, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.7339366528010748, "learning_rate": 3.9189859472289956e-05, "loss": 0.6175, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6687000838994336, "learning_rate": 3.9173849578646324e-05, "loss": 0.5761, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6340620950001628, "learning_rate": 3.9157686371412395e-05, "loss": 0.6092, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.6718127078165036, "learning_rate": 3.914136997982874e-05, "loss": 0.6143, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.7013004315402418, "learning_rate": 3.912490053436079e-05, "loss": 0.6064, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5924501487680419, "learning_rate": 3.9108278166697805e-05, "loss": 0.6469, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.6795641250284999, "learning_rate": 3.909150300975178e-05, "loss": 0.8285, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.653273098770846, "learning_rate": 3.907457519765642e-05, "loss": 0.618, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5822168723687806, "learning_rate": 3.905749486576607e-05, "loss": 0.5628, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.7050671922480827, "learning_rate": 3.90402621506546e-05, "loss": 0.6201, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.7182128717260565, "learning_rate": 3.902287719011435e-05, "loss": 0.6497, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.6956445752647477, "learning_rate": 3.900534012315499e-05, "loss": 0.5804, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.7486128988205332, "learning_rate": 3.8987651090002454e-05, "loss": 0.6201, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7966597960767878, "learning_rate": 3.896981023209777e-05, "loss": 0.6515, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.740248700193152, "learning_rate": 3.8951817692095966e-05, "loss": 0.61, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 1.27133178773966, "learning_rate": 3.893367361386491e-05, "loss": 0.6306, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.7521447847543766, "learning_rate": 3.891537814248417e-05, "loss": 0.5924, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.6291492145625717, "learning_rate": 3.889693142424384e-05, "loss": 0.5908, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.6840280654105778, "learning_rate": 3.8878333606643405e-05, "loss": 0.7172, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6461313485721801, "learning_rate": 3.885958483839049e-05, "loss": 0.7687, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.727975003764745, "learning_rate": 3.8840685269399786e-05, "loss": 0.6169, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.6638077618148115, "learning_rate": 3.882163505079171e-05, "loss": 0.6209, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.7760419037069751, "learning_rate": 3.880243433489132e-05, "loss": 0.6158, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.7668136386830358, "learning_rate": 3.878308327522702e-05, "loss": 0.4852, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.6048947106104052, "learning_rate": 3.876358202652936e-05, "loss": 0.447, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 13.986862231826915, "learning_rate": 3.8743930744729835e-05, "loss": 0.4577, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.9495136085785605, "learning_rate": 3.8724129586959535e-05, "loss": 0.4761, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.7754552891216772, "learning_rate": 3.870417871154801e-05, "loss": 0.4449, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6951199290408371, "learning_rate": 3.868407827802192e-05, "loss": 0.5064, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.69365206274664, "learning_rate": 3.8663828447103804e-05, "loss": 0.4627, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.7166005919765355, "learning_rate": 3.8643429380710765e-05, "loss": 0.4358, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.7473062483229409, "learning_rate": 3.862288124195319e-05, "loss": 0.4305, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.631406409712458, "learning_rate": 3.8602184195133464e-05, "loss": 0.4489, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.6933509392448941, "learning_rate": 3.8581338405744604e-05, "loss": 0.4208, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.7427715399230702, "learning_rate": 3.8560344040468996e-05, "loss": 0.456, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.7701938122417438, "learning_rate": 3.853920126717703e-05, "loss": 0.4725, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6853425489975769, "learning_rate": 3.851791025492574e-05, "loss": 0.4521, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.9305840709834884, "learning_rate": 3.8496471173957515e-05, "loss": 0.4226, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.9292078702153517, "learning_rate": 3.847488419569866e-05, "loss": 0.4765, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.8373718404561735, "learning_rate": 3.8453149492758077e-05, "loss": 0.4472, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.8112651223736691, "learning_rate": 3.8431267238925886e-05, "loss": 0.4448, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.750421344631621, "learning_rate": 3.840923760917199e-05, "loss": 0.4432, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.8071028799237825, "learning_rate": 3.838706077964473e-05, "loss": 0.4623, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.7779568940121794, "learning_rate": 3.836473692766944e-05, "loss": 0.5027, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.6325437377637405, "learning_rate": 3.834226623174705e-05, "loss": 0.4529, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.7539700513024735, "learning_rate": 3.831964887155264e-05, "loss": 0.4766, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6833442653673221, "learning_rate": 3.829688502793403e-05, "loss": 0.5473, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 1.283744886012787, "learning_rate": 3.827397488291029e-05, "loss": 0.6465, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.616831832324564, "learning_rate": 3.8250918619670343e-05, "loss": 0.4458, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.6419417251415873, "learning_rate": 3.822771642257145e-05, "loss": 0.4645, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.6044556204674933, "learning_rate": 3.820436847713776e-05, "loss": 0.5675, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.7256607927167583, "learning_rate": 3.8180874970058826e-05, "loss": 0.4444, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.6937887417854193, "learning_rate": 3.8157236089188103e-05, "loss": 0.4918, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.7089512644566953, "learning_rate": 3.813345202354145e-05, "loss": 0.4182, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6914284772718505, "learning_rate": 3.810952296329563e-05, "loss": 0.4485, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.6930017397989532, "learning_rate": 3.808544909978676e-05, "loss": 0.4376, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.6950697773798492, "learning_rate": 3.806123062550882e-05, "loss": 0.5108, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.6611900745144518, "learning_rate": 3.803686773411208e-05, "loss": 0.4914, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.6794235269059249, "learning_rate": 3.801236062040158e-05, "loss": 0.4475, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.745681065877009, "learning_rate": 3.798770948033553e-05, "loss": 0.4359, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.6130794610453373, "learning_rate": 3.796291451102381e-05, "loss": 0.4477, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6670480579110434, "learning_rate": 3.793797591072631e-05, "loss": 0.4218, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.7732343798643938, "learning_rate": 3.791289387885144e-05, "loss": 0.4303, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.6759805742664613, "learning_rate": 3.788766861595443e-05, "loss": 0.4389, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.75515634603268, "learning_rate": 3.7862300323735835e-05, "loss": 0.4601, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.7292016561360979, "learning_rate": 3.783678920503983e-05, "loss": 0.4607, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.7176540567493296, "learning_rate": 3.781113546385265e-05, "loss": 0.4472, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.67114042878583, "learning_rate": 3.7785339305300916e-05, "loss": 0.4469, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6839282630832858, "learning_rate": 3.7759400935650025e-05, "loss": 0.6264, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.6951979744289044, "learning_rate": 3.77333205623025e-05, "loss": 0.4445, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.6734356266182856, "learning_rate": 3.7707098393796295e-05, "loss": 0.4253, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.6658299286822078, "learning_rate": 3.7680734639803185e-05, "loss": 0.4534, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.7021590889094128, "learning_rate": 3.765422951112704e-05, "loss": 0.42, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.984820456520494, "learning_rate": 3.762758321970216e-05, "loss": 0.816, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.6042866493683782, "learning_rate": 3.7600795978591584e-05, "loss": 0.4216, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 1.3912823952435844, "learning_rate": 3.757386800198538e-05, "loss": 0.5403, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.760537819352268, "learning_rate": 3.7546799505198925e-05, "loss": 0.4102, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.6639441370587623, "learning_rate": 3.7519590704671197e-05, "loss": 0.4583, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.612828804974813, "learning_rate": 3.749224181796305e-05, "loss": 0.5002, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5431333034330023, "learning_rate": 3.746475306375545e-05, "loss": 0.4169, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.6852648765168173, "learning_rate": 3.743712466184774e-05, "loss": 0.3932, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.6772355935144633, "learning_rate": 3.7409356833155885e-05, "loss": 0.4651, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.7067598092267349, "learning_rate": 3.73814497997107e-05, "loss": 0.466, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.6356887931095296, "learning_rate": 3.7353403784656095e-05, "loss": 0.4262, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.6164943325698601, "learning_rate": 3.732521901224724e-05, "loss": 0.4229, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6317540340459735, "learning_rate": 3.7296895707848844e-05, "loss": 0.4417, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.7569131382838492, "learning_rate": 3.7268434097933275e-05, "loss": 0.4592, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.7317743803081661, "learning_rate": 3.723983441007882e-05, "loss": 0.4587, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.6640570034063965, "learning_rate": 3.721109687296781e-05, "loss": 0.4955, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 1.0123024734475174, "learning_rate": 3.718222171638484e-05, "loss": 0.5571, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.7223289372787612, "learning_rate": 3.715320917121488e-05, "loss": 0.5347, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.6293421224705728, "learning_rate": 3.712405946944149e-05, "loss": 0.4441, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6639236057616215, "learning_rate": 3.709477284414488e-05, "loss": 0.4446, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.6116059751604079, "learning_rate": 3.7065349529500136e-05, "loss": 0.4539, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.9555945199306705, "learning_rate": 3.7035789760775305e-05, "loss": 0.4282, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 5.357730745370626, "learning_rate": 3.70060937743295e-05, "loss": 0.4774, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.7348320635813934, "learning_rate": 3.6976261807611045e-05, "loss": 0.4926, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.6929781027320011, "learning_rate": 3.694629409915555e-05, "loss": 0.4625, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6565113677481302, "learning_rate": 3.691619088858401e-05, "loss": 0.4774, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5914610739502529, "learning_rate": 3.68859524166009e-05, "loss": 0.4134, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.7647466548462671, "learning_rate": 3.6855578924992226e-05, "loss": 0.4699, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.5782518844265966, "learning_rate": 3.6825070656623626e-05, "loss": 0.4262, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.6837770002402523, "learning_rate": 3.67944278554384e-05, "loss": 0.4451, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.6458063056296287, "learning_rate": 3.676365076645557e-05, "loss": 0.4392, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.5317841690284812, "learning_rate": 3.673273963576791e-05, "loss": 0.4135, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6269909624524852, "learning_rate": 3.670169471054001e-05, "loss": 0.4993, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.6537434529651132, "learning_rate": 3.6670516239006254e-05, "loss": 0.4701, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.5957541395017204, "learning_rate": 3.663920447046888e-05, "loss": 0.4444, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.6394599296396221, "learning_rate": 3.6607759655295954e-05, "loss": 0.4509, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.6164054005589452, "learning_rate": 3.657618204491937e-05, "loss": 0.4837, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.5984863124596408, "learning_rate": 3.6544471891832875e-05, "loss": 0.415, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.6454738947397438, "learning_rate": 3.6512629449589983e-05, "loss": 0.4781, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.7124093800643541, "learning_rate": 3.6480654972802045e-05, "loss": 0.5487, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5949982076373278, "learning_rate": 3.644854871713611e-05, "loss": 0.4386, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.6038981532009374, "learning_rate": 3.6416310939312924e-05, "loss": 0.4683, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.7217738291888025, "learning_rate": 3.638394189710493e-05, "loss": 0.4593, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.5828265750804303, "learning_rate": 3.635144184933412e-05, "loss": 0.4289, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.7236335655237441, "learning_rate": 3.6318811055869994e-05, "loss": 0.4904, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.6359326125169049, "learning_rate": 3.628604977762752e-05, "loss": 0.4887, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.7576429473549477, "learning_rate": 3.6253158276565004e-05, "loss": 0.4335, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5759031507573272, "learning_rate": 3.6220136815682016e-05, "loss": 0.4212, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.7518065940986095, "learning_rate": 3.618698565901727e-05, "loss": 0.4491, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.6734796646506233, "learning_rate": 3.615370507164654e-05, "loss": 0.4195, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.7126221773561657, "learning_rate": 3.61202953196805e-05, "loss": 0.4263, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.7863067570832918, "learning_rate": 3.6086756670262654e-05, "loss": 0.4604, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.6835290428141996, "learning_rate": 3.6053089391567135e-05, "loss": 0.4974, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.5456630828712649, "learning_rate": 3.601929375279662e-05, "loss": 0.4273, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.6088658155120229, "learning_rate": 3.598537002418012e-05, "loss": 0.4708, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.6705970311614605, "learning_rate": 3.5951318476970885e-05, "loss": 0.4762, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5350628837046364, "learning_rate": 3.591713938344416e-05, "loss": 0.4422, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.5321239310794325, "learning_rate": 3.588283301689507e-05, "loss": 0.4027, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.6442409796021845, "learning_rate": 3.5848399651636424e-05, "loss": 0.3941, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.6643309684091782, "learning_rate": 3.5813839562996473e-05, "loss": 0.4149, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5342557263748285, "learning_rate": 3.5779153027316775e-05, "loss": 0.401, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.6728190309215012, "learning_rate": 3.574434032194994e-05, "loss": 0.6037, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.669823538306523, "learning_rate": 3.5709401725257436e-05, "loss": 0.4437, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.5520838578077726, "learning_rate": 3.5674337516607346e-05, "loss": 0.4369, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.6501923409435936, "learning_rate": 3.563914797637216e-05, "loss": 0.6656, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5695812767351902, "learning_rate": 3.560383338592649e-05, "loss": 0.4676, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.6886288866299405, "learning_rate": 3.556839402764487e-05, "loss": 0.5039, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 2.957107765930523, "learning_rate": 3.553283018489946e-05, "loss": 0.5813, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.6496289817423581, "learning_rate": 3.54971421420578e-05, "loss": 0.4163, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.629002629403064, "learning_rate": 3.5461330184480524e-05, "loss": 0.4409, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.5821949930288115, "learning_rate": 3.54253945985191e-05, "loss": 0.4402, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.6015268135815072, "learning_rate": 3.5389335671513524e-05, "loss": 0.4649, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.6620077983875352, "learning_rate": 3.5353153691789986e-05, "loss": 0.4609, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.7348265342351968, "learning_rate": 3.531684894865866e-05, "loss": 0.4282, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.6736706202331719, "learning_rate": 3.528042173241128e-05, "loss": 0.4611, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.6376174234080234, "learning_rate": 3.524387233431892e-05, "loss": 0.4337, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.7039628862143869, "learning_rate": 3.520720104662958e-05, "loss": 0.4853, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.6516372550447935, "learning_rate": 3.5170408162565904e-05, "loss": 0.4712, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.739601752532943, "learning_rate": 3.513349397632281e-05, "loss": 0.4331, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.636344209150471, "learning_rate": 3.5096458783065145e-05, "loss": 0.4456, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.7119568148713307, "learning_rate": 3.505930287892533e-05, "loss": 0.4686, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.6887534803750219, "learning_rate": 3.502202656100099e-05, "loss": 0.4799, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.6733718288684819, "learning_rate": 3.498463012735256e-05, "loss": 0.4603, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.8205306772839278, "learning_rate": 3.494711387700094e-05, "loss": 0.4673, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.6044520202230044, "learning_rate": 3.490947810992505e-05, "loss": 0.4283, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.6876600986486895, "learning_rate": 3.48717231270595e-05, "loss": 0.4414, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.7355079905029146, "learning_rate": 3.483384923029211e-05, "loss": 0.4478, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.6433690356030608, "learning_rate": 3.479585672246156e-05, "loss": 0.4562, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.6056730892063952, "learning_rate": 3.4757745907354924e-05, "loss": 0.4718, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 1.0596120818417984, "learning_rate": 3.471951708970527e-05, "loss": 0.509, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.7507633845869278, "learning_rate": 3.468117057518921e-05, "loss": 0.4699, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.8881283532393015, "learning_rate": 3.4642706670424426e-05, "loss": 0.4986, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.6314227445213361, "learning_rate": 3.460412568296731e-05, "loss": 0.4575, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.7153921891813905, "learning_rate": 3.456542792131039e-05, "loss": 0.4786, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.6786110386298617, "learning_rate": 3.4526613694879936e-05, "loss": 0.4573, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.7568176836608699, "learning_rate": 3.448768331403348e-05, "loss": 0.449, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.6322421255957232, "learning_rate": 3.44486370900573e-05, "loss": 0.4245, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.7287207445568646, "learning_rate": 3.440947533516396e-05, "loss": 0.4725, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.6722653922741815, "learning_rate": 3.4370198362489816e-05, "loss": 0.5369, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.7003843257607393, "learning_rate": 3.43308064860925e-05, "loss": 0.4631, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.6632685569740013, "learning_rate": 3.4291300020948393e-05, "loss": 0.431, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.5340371313448409, "learning_rate": 3.425167928295015e-05, "loss": 0.4476, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.652230062250246, "learning_rate": 3.421194458890411e-05, "loss": 0.6332, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.7094119144151665, "learning_rate": 3.4172096256527865e-05, "loss": 0.4768, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5615266659471407, "learning_rate": 3.4132134604447595e-05, "loss": 0.4498, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.7660716837490738, "learning_rate": 3.409205995219561e-05, "loss": 0.4329, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.6872013413342777, "learning_rate": 3.4051872620207765e-05, "loss": 0.4657, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.6879064744792248, "learning_rate": 3.40115729298209e-05, "loss": 0.4666, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.7028785155375341, "learning_rate": 3.397116120327025e-05, "loss": 0.4326, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.6233886102035991, "learning_rate": 3.3930637763686916e-05, "loss": 0.4469, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.5762835523797407, "learning_rate": 3.389000293509524e-05, "loss": 0.4614, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.6494189843884206, "learning_rate": 3.3849257042410225e-05, "loss": 0.4317, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.6173401847502868, "learning_rate": 3.380840041143494e-05, "loss": 0.4601, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.7394572274784478, "learning_rate": 3.376743336885792e-05, "loss": 0.4655, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.6530708593866718, "learning_rate": 3.372635624225055e-05, "loss": 0.4497, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.72014794098277, "learning_rate": 3.3685169360064445e-05, "loss": 0.4664, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.5870130244400494, "learning_rate": 3.3643873051628804e-05, "loss": 0.4559, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.5779343378751729, "learning_rate": 3.3602467647147814e-05, "loss": 0.4585, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.6796570854444397, "learning_rate": 3.356095347769799e-05, "loss": 0.4792, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.7354921100265597, "learning_rate": 3.351933087522552e-05, "loss": 0.4475, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.6381851482103231, "learning_rate": 3.3477600172543626e-05, "loss": 0.4836, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.6965540932227807, "learning_rate": 3.3435761703329894e-05, "loss": 0.4694, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.6616947725416761, "learning_rate": 3.3393815802123606e-05, "loss": 0.4183, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.6264235007486447, "learning_rate": 3.335176280432308e-05, "loss": 0.4338, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.7156274942209494, "learning_rate": 3.330960304618295e-05, "loss": 0.4326, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.6176526959360797, "learning_rate": 3.326733686481153e-05, "loss": 0.456, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.6074742401400387, "learning_rate": 3.3224964598168084e-05, "loss": 0.4173, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.6552595072740552, "learning_rate": 3.318248658506012e-05, "loss": 0.4386, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.6775329358107801, "learning_rate": 3.313990316514069e-05, "loss": 0.4977, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.7505239114245388, "learning_rate": 3.309721467890571e-05, "loss": 0.4442, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.6787513291255542, "learning_rate": 3.305442146769115e-05, "loss": 0.4798, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.565191288453011, "learning_rate": 3.30115238736704e-05, "loss": 0.4296, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.6053867612075058, "learning_rate": 3.296852223985148e-05, "loss": 0.4691, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.6295682440436912, "learning_rate": 3.2925416910074315e-05, "loss": 0.4281, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.7065582099847417, "learning_rate": 3.288220822900796e-05, "loss": 0.4438, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.5835803880993764, "learning_rate": 3.283889654214788e-05, "loss": 0.4338, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.7074065075428065, "learning_rate": 3.279548219581317e-05, "loss": 0.4535, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.6586960550009276, "learning_rate": 3.275196553714379e-05, "loss": 0.4442, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.6728737531015232, "learning_rate": 3.270834691409778e-05, "loss": 0.4667, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.5940321188055903, "learning_rate": 3.266462667544849e-05, "loss": 0.4475, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.6404111767730662, "learning_rate": 3.262080517078178e-05, "loss": 0.6447, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.5495648594902417, "learning_rate": 3.257688275049323e-05, "loss": 0.4302, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.7193710095651576, "learning_rate": 3.253285976578535e-05, "loss": 0.4427, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.6338062408899547, "learning_rate": 3.2488736568664756e-05, "loss": 0.4815, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.724828654279895, "learning_rate": 3.244451351193935e-05, "loss": 0.4551, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.6318468313193015, "learning_rate": 3.240019094921551e-05, "loss": 0.4066, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.675544589507006, "learning_rate": 3.235576923489527e-05, "loss": 0.468, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.6979440737214379, "learning_rate": 3.2311248724173476e-05, "loss": 0.5397, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5922571266781367, "learning_rate": 3.226662977303494e-05, "loss": 0.4667, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.8461059416593152, "learning_rate": 3.2221912738251626e-05, "loss": 0.4645, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.5967178531797268, "learning_rate": 3.2177097977379736e-05, "loss": 0.4637, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.5939535119084902, "learning_rate": 3.21321858487569e-05, "loss": 0.4797, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.6446682244365692, "learning_rate": 3.208717671149931e-05, "loss": 0.4172, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.7032969765473511, "learning_rate": 3.204207092549882e-05, "loss": 0.4345, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.5877378259338976, "learning_rate": 3.19968688514201e-05, "loss": 0.4496, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.7000283308666556, "learning_rate": 3.195157085069774e-05, "loss": 0.4698, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.7638590714853728, "learning_rate": 3.190617728553332e-05, "loss": 0.479, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.6644724631157978, "learning_rate": 3.1860688518892606e-05, "loss": 0.4602, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.5034970828336585, "learning_rate": 3.181510491450254e-05, "loss": 0.4362, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.6007303801536568, "learning_rate": 3.176942683684842e-05, "loss": 0.4161, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.5828554937723477, "learning_rate": 3.1723654651170934e-05, "loss": 0.4416, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.5930195790428412, "learning_rate": 3.167778872346327e-05, "loss": 0.4016, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.5270042183035054, "learning_rate": 3.163182942046815e-05, "loss": 0.4276, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.521547094261582, "learning_rate": 3.158577710967494e-05, "loss": 0.4371, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.5976959860594396, "learning_rate": 3.153963215931669e-05, "loss": 0.4354, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.613005022025149, "learning_rate": 3.14933949383672e-05, "loss": 0.4583, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 2.494828491597805, "learning_rate": 3.144706581653805e-05, "loss": 0.4628, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.5675461138040903, "learning_rate": 3.140064516427566e-05, "loss": 0.5503, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.6271207143382409, "learning_rate": 3.135413335275833e-05, "loss": 0.4948, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.7063423151076784, "learning_rate": 3.130753075389327e-05, "loss": 0.4563, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.6026451090088365, "learning_rate": 3.1260837740313625e-05, "loss": 0.5938, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.5947645740971516, "learning_rate": 3.121405468537547e-05, "loss": 0.4209, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.5656526064398855, "learning_rate": 3.116718196315488e-05, "loss": 0.4293, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.7046889602930683, "learning_rate": 3.1120219948444894e-05, "loss": 0.4596, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.5743229308180353, "learning_rate": 3.107316901675252e-05, "loss": 0.4479, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.6466771666919304, "learning_rate": 3.1026029544295745e-05, "loss": 0.448, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.5856646670102074, "learning_rate": 3.097880190800057e-05, "loss": 0.4273, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.6176994417702354, "learning_rate": 3.093148648549788e-05, "loss": 0.4793, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 2.227587750744935, "learning_rate": 3.088408365512055e-05, "loss": 0.561, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.9661626492371088, "learning_rate": 3.083659379590034e-05, "loss": 0.5187, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.5557965906885138, "learning_rate": 3.0789017287564913e-05, "loss": 0.4617, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.6811319084156807, "learning_rate": 3.074135451053475e-05, "loss": 0.4325, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.5994744594823571, "learning_rate": 3.069360584592015e-05, "loss": 0.4387, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.5669486717972468, "learning_rate": 3.064577167551816e-05, "loss": 0.4013, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.47742430627165566, "learning_rate": 3.059785238180953e-05, "loss": 0.4408, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.5949405911702703, "learning_rate": 3.054984834795566e-05, "loss": 0.4477, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.591685513410584, "learning_rate": 3.0501759957795537e-05, "loss": 0.4335, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.6469190231393196, "learning_rate": 3.0453587595842627e-05, "loss": 0.4541, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.5780492458104068, "learning_rate": 3.0405331647281856e-05, "loss": 0.4777, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.5829165029395755, "learning_rate": 3.0356992497966508e-05, "loss": 0.6068, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.6078291192274377, "learning_rate": 3.0308570534415137e-05, "loss": 0.449, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.5660280091237021, "learning_rate": 3.0260066143808467e-05, "loss": 0.4307, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.8419050433336811, "learning_rate": 3.021147971398632e-05, "loss": 0.4466, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.6431254380452485, "learning_rate": 3.0162811633444478e-05, "loss": 0.4822, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.6027091987154364, "learning_rate": 3.0114062291331635e-05, "loss": 0.4361, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.5753258369287028, "learning_rate": 3.0065232077446217e-05, "loss": 0.4453, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.7542786211581112, "learning_rate": 3.001632138223332e-05, "loss": 0.4619, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.677394610495847, "learning_rate": 2.9967330596781565e-05, "loss": 0.369, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.537180942197941, "learning_rate": 2.9918260112819952e-05, "loss": 0.316, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.8309916774567144, "learning_rate": 2.9869110322714778e-05, "loss": 0.3238, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.7146301083564642, "learning_rate": 2.9819881619466447e-05, "loss": 0.3547, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.6063114030096397, "learning_rate": 2.9770574396706364e-05, "loss": 0.3034, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5842287660139313, "learning_rate": 2.972118904869376e-05, "loss": 0.3384, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.5866969749463898, "learning_rate": 2.9671725970312563e-05, "loss": 0.2775, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.6579613711126869, "learning_rate": 2.9622185557068238e-05, "loss": 0.3218, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.6635122814204271, "learning_rate": 2.95725682050846e-05, "loss": 0.2838, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.5967221351543726, "learning_rate": 2.9522874311100684e-05, "loss": 0.3163, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.6585082183031565, "learning_rate": 2.9473104272467526e-05, "loss": 0.2992, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.7334352625809847, "learning_rate": 2.942325848714505e-05, "loss": 0.2869, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.5804679974595853, "learning_rate": 2.9373337353698804e-05, "loss": 0.2761, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.6145755382817409, "learning_rate": 2.932334127129686e-05, "loss": 0.4212, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.6399713458837865, "learning_rate": 2.9273270639706547e-05, "loss": 0.2701, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.5638194627051085, "learning_rate": 2.922312585929131e-05, "loss": 0.2617, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.5275112448247352, "learning_rate": 2.9172907331007478e-05, "loss": 0.3416, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.5129748806524072, "learning_rate": 2.9122615456401053e-05, "loss": 0.4048, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.5498414456029534, "learning_rate": 2.9072250637604535e-05, "loss": 0.3764, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.5778591426176211, "learning_rate": 2.9021813277333667e-05, "loss": 0.2882, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.6053090269873191, "learning_rate": 2.8971303778884244e-05, "loss": 0.2822, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.555766239337971, "learning_rate": 2.8920722546128863e-05, "loss": 0.275, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.6081680668146087, "learning_rate": 2.887006998351372e-05, "loss": 0.419, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.5199371777657582, "learning_rate": 2.881934649605535e-05, "loss": 0.306, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.5173807296851285, "learning_rate": 2.8768552489337408e-05, "loss": 0.3999, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.5787276036325502, "learning_rate": 2.8717688369507425e-05, "loss": 0.2889, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.5182444798172139, "learning_rate": 2.8666754543273535e-05, "loss": 0.2873, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.519127327775822, "learning_rate": 2.8615751417901273e-05, "loss": 0.302, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.5996301355585285, "learning_rate": 2.856467940121025e-05, "loss": 0.3124, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.6600916590572561, "learning_rate": 2.8513538901570964e-05, "loss": 0.275, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.5776777386801081, "learning_rate": 2.846233032790149e-05, "loss": 0.2881, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.536336772258433, "learning_rate": 2.84110540896642e-05, "loss": 0.277, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.5489529711181104, "learning_rate": 2.8359710596862555e-05, "loss": 0.3098, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.5955140071525451, "learning_rate": 2.8308300260037734e-05, "loss": 0.2725, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.5687954937056864, "learning_rate": 2.8256823490265424e-05, "loss": 0.3341, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.500102504732542, "learning_rate": 2.8205280699152515e-05, "loss": 0.3118, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.7022820887477754, "learning_rate": 2.8153672298833777e-05, "loss": 0.3042, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.5525051930796203, "learning_rate": 2.8101998701968615e-05, "loss": 0.3091, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.563003286294092, "learning_rate": 2.805026032173773e-05, "loss": 0.3117, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.535945784075937, "learning_rate": 2.7998457571839832e-05, "loss": 0.3017, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.6746669036126783, "learning_rate": 2.7946590866488322e-05, "loss": 0.2749, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.5443185955188488, "learning_rate": 2.7894660620408e-05, "loss": 0.3534, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.7581585018363689, "learning_rate": 2.784266724883173e-05, "loss": 0.2866, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.5399333704332238, "learning_rate": 2.7790611167497128e-05, "loss": 0.2699, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.6026735894767306, "learning_rate": 2.7738492792643224e-05, "loss": 0.2573, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.6146714642760363, "learning_rate": 2.768631254100716e-05, "loss": 0.2746, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.5514009471325881, "learning_rate": 2.7634070829820836e-05, "loss": 0.2397, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.5579012787609748, "learning_rate": 2.7581768076807592e-05, "loss": 0.3185, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.5657900057252903, "learning_rate": 2.7529404700178832e-05, "loss": 0.2931, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.708737986174433, "learning_rate": 2.7476981118630735e-05, "loss": 0.2949, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.5819606877876045, "learning_rate": 2.742449775134085e-05, "loss": 0.2837, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.5089211504645136, "learning_rate": 2.7371955017964788e-05, "loss": 0.3194, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.5278984686126784, "learning_rate": 2.7319353338632845e-05, "loss": 0.3003, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.5550380043857871, "learning_rate": 2.7266693133946645e-05, "loss": 0.2975, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.7376941846205278, "learning_rate": 2.7213974824975785e-05, "loss": 0.2812, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.5207666032982179, "learning_rate": 2.7161198833254464e-05, "loss": 0.2869, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.502205370209877, "learning_rate": 2.7108365580778095e-05, "loss": 0.3147, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.5308075746315769, "learning_rate": 2.705547548999996e-05, "loss": 0.2864, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.5287899860110656, "learning_rate": 2.7002528983827817e-05, "loss": 0.3196, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.6085588147176054, "learning_rate": 2.6949526485620517e-05, "loss": 0.3638, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.6399658067934839, "learning_rate": 2.6896468419184623e-05, "loss": 0.3263, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.5797811517457103, "learning_rate": 2.6843355208771024e-05, "loss": 0.2581, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.5484083736298625, "learning_rate": 2.6790187279071536e-05, "loss": 0.2492, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.5190822803814198, "learning_rate": 2.67369650552155e-05, "loss": 0.5545, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.5868539162040792, "learning_rate": 2.6683688962766407e-05, "loss": 0.321, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.6020217128697771, "learning_rate": 2.6630359427718468e-05, "loss": 0.2999, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.5393103099018282, "learning_rate": 2.6576976876493225e-05, "loss": 0.2515, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.55281500605695, "learning_rate": 2.652354173593614e-05, "loss": 0.3298, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.6016421590399252, "learning_rate": 2.647005443331317e-05, "loss": 0.3176, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.5820108133601682, "learning_rate": 2.6416515396307354e-05, "loss": 0.4916, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.5897984063351597, "learning_rate": 2.636292505301542e-05, "loss": 0.3428, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.541302556067417, "learning_rate": 2.630928383194431e-05, "loss": 0.3202, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.5378477105297512, "learning_rate": 2.625559216200781e-05, "loss": 0.3289, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5659027800808052, "learning_rate": 2.620185047252308e-05, "loss": 0.2933, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.6219659889530368, "learning_rate": 2.614805919320723e-05, "loss": 0.315, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.530568328467094, "learning_rate": 2.6094218754173895e-05, "loss": 0.2932, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.558824777221399, "learning_rate": 2.60403295859298e-05, "loss": 0.3765, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.575641142182581, "learning_rate": 2.5986392119371297e-05, "loss": 0.2729, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.5053867728737027, "learning_rate": 2.5932406785780928e-05, "loss": 0.3287, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.5520718848472498, "learning_rate": 2.5878374016823987e-05, "loss": 0.2836, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.535570610202801, "learning_rate": 2.5824294244545045e-05, "loss": 0.284, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.6319815809890227, "learning_rate": 2.577016790136453e-05, "loss": 0.294, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.6164036503375183, "learning_rate": 2.5715995420075225e-05, "loss": 0.329, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.6736036629368823, "learning_rate": 2.5661777233838864e-05, "loss": 0.245, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.6980094170245955, "learning_rate": 2.5607513776182616e-05, "loss": 0.2935, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.5893749630084683, "learning_rate": 2.5553205480995633e-05, "loss": 0.2702, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.5464723414383053, "learning_rate": 2.5498852782525604e-05, "loss": 0.2972, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.5895082175564226, "learning_rate": 2.5444456115375252e-05, "loss": 0.3045, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.6270267923802216, "learning_rate": 2.539001591449889e-05, "loss": 0.3108, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.8242443283982168, "learning_rate": 2.53355326151989e-05, "loss": 0.2793, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.5473440505861816, "learning_rate": 2.5281006653122288e-05, "loss": 0.3011, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.5348050417573359, "learning_rate": 2.5226438464257217e-05, "loss": 0.3016, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.5153438435854717, "learning_rate": 2.5171828484929447e-05, "loss": 0.2727, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.5631433461014027, "learning_rate": 2.5117177151798934e-05, "loss": 0.2953, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.5904832935363445, "learning_rate": 2.506248490185627e-05, "loss": 0.2876, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.7523567822115471, "learning_rate": 2.500775217241923e-05, "loss": 0.3158, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.5438493475488481, "learning_rate": 2.4952979401129266e-05, "loss": 0.3111, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.5088091556358274, "learning_rate": 2.4898167025948e-05, "loss": 0.3099, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.6502837539192319, "learning_rate": 2.4843315485153703e-05, "loss": 0.3299, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.5969017111257767, "learning_rate": 2.4788425217337856e-05, "loss": 0.2912, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.5378373496943839, "learning_rate": 2.4733496661401572e-05, "loss": 0.2897, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.5636351205134157, "learning_rate": 2.4678530256552114e-05, "loss": 0.2944, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.5845454111500652, "learning_rate": 2.46235264422994e-05, "loss": 0.2897, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.627288759943557, "learning_rate": 2.4568485658452452e-05, "loss": 0.3086, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.5570915654520955, "learning_rate": 2.451340834511592e-05, "loss": 0.3123, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.5072758969870501, "learning_rate": 2.4458294942686528e-05, "loss": 0.2592, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.49679417049374996, "learning_rate": 2.440314589184958e-05, "loss": 0.3106, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.5475500087934766, "learning_rate": 2.434796163357541e-05, "loss": 0.2835, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.6388023469167671, "learning_rate": 2.429274260911588e-05, "loss": 0.3019, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.5504908614370223, "learning_rate": 2.423748926000084e-05, "loss": 0.2387, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.5289864547001905, "learning_rate": 2.418220202803459e-05, "loss": 0.2979, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.5175594700332614, "learning_rate": 2.412688135529237e-05, "loss": 0.275, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.6025486303938795, "learning_rate": 2.4071527684116807e-05, "loss": 0.2786, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.6470367740601976, "learning_rate": 2.4016141457114372e-05, "loss": 0.2881, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.5115595253118713, "learning_rate": 2.396072311715187e-05, "loss": 0.3845, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.5831766128943909, "learning_rate": 2.3905273107352863e-05, "loss": 0.2944, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.5172736301745011, "learning_rate": 2.3849791871094157e-05, "loss": 0.2827, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.5077216634645652, "learning_rate": 2.379427985200223e-05, "loss": 0.2844, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.6122762387802626, "learning_rate": 2.373873749394972e-05, "loss": 0.3035, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.5253056678612938, "learning_rate": 2.3683165241051836e-05, "loss": 0.2961, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.552598930784239, "learning_rate": 2.3627563537662823e-05, "loss": 0.3744, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.561636450138344, "learning_rate": 2.3571932828372433e-05, "loss": 0.2551, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.5789989554253864, "learning_rate": 2.351627355800233e-05, "loss": 0.321, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.5227221337760213, "learning_rate": 2.346058617160256e-05, "loss": 0.3078, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.503086279625639, "learning_rate": 2.3404871114447976e-05, "loss": 0.2887, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.4911711169660155, "learning_rate": 2.334912883203469e-05, "loss": 0.3085, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.5700964586594314, "learning_rate": 2.3293359770076505e-05, "loss": 0.3001, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.5141218322257165, "learning_rate": 2.323756437450136e-05, "loss": 0.2996, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.550117488542594, "learning_rate": 2.3181743091447754e-05, "loss": 0.3047, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.4974842274938465, "learning_rate": 2.3125896367261164e-05, "loss": 0.279, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.542183331795815, "learning_rate": 2.307002464849052e-05, "loss": 0.2739, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.5383572004612254, "learning_rate": 2.30141283818846e-05, "loss": 0.2694, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.5961844939142117, "learning_rate": 2.2958208014388462e-05, "loss": 0.3074, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.5497374827808077, "learning_rate": 2.2902263993139857e-05, "loss": 0.3294, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.6120546821513423, "learning_rate": 2.2846296765465708e-05, "loss": 0.2569, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.6096347900148847, "learning_rate": 2.2790306778878465e-05, "loss": 0.253, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.5603645349351446, "learning_rate": 2.273429448107257e-05, "loss": 0.2908, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.5852089167193227, "learning_rate": 2.2678260319920868e-05, "loss": 0.311, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.6749330246052574, "learning_rate": 2.262220474347102e-05, "loss": 0.2863, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.5965523217993658, "learning_rate": 2.2566128199941918e-05, "loss": 0.2993, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.6250201553054023, "learning_rate": 2.2510031137720104e-05, "loss": 0.322, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.5491365984393151, "learning_rate": 2.2453914005356206e-05, "loss": 0.2924, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.5780590789881493, "learning_rate": 2.2397777251561302e-05, "loss": 0.306, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.640147384256183, "learning_rate": 2.2341621325203393e-05, "loss": 0.2823, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.5398511202525778, "learning_rate": 2.2285446675303764e-05, "loss": 0.293, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.4982613501636393, "learning_rate": 2.2229253751033423e-05, "loss": 0.2942, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.5531097152473149, "learning_rate": 2.2173043001709492e-05, "loss": 0.3318, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.6356039592431048, "learning_rate": 2.2116814876791627e-05, "loss": 0.2879, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.5747205868715698, "learning_rate": 2.2060569825878413e-05, "loss": 0.3027, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.5255116440485635, "learning_rate": 2.2004308298703777e-05, "loss": 0.2626, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.5835663174782475, "learning_rate": 2.1948030745133396e-05, "loss": 0.2555, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.6554463585764992, "learning_rate": 2.1891737615161083e-05, "loss": 0.2868, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.5683623900347771, "learning_rate": 2.1835429358905218e-05, "loss": 0.2866, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.5675461949653711, "learning_rate": 2.17791064266051e-05, "loss": 0.2903, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.4850799830339846, "learning_rate": 2.172276926861741e-05, "loss": 0.3196, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.49170772632973614, "learning_rate": 2.166641833541255e-05, "loss": 0.3098, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.577088827130892, "learning_rate": 2.161005407757109e-05, "loss": 0.295, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.6037351257173962, "learning_rate": 2.155367694578013e-05, "loss": 0.2955, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.5865356565835083, "learning_rate": 2.1497287390829712e-05, "loss": 0.2801, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.581363878413078, "learning_rate": 2.1440885863609208e-05, "loss": 0.2955, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.6422557045195476, "learning_rate": 2.1384472815103737e-05, "loss": 0.322, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.6210081668763394, "learning_rate": 2.1328048696390534e-05, "loss": 0.3037, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.505591987746427, "learning_rate": 2.1271613958635342e-05, "loss": 0.3161, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.5273405170539797, "learning_rate": 2.1215169053088825e-05, "loss": 0.3023, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.531926484768458, "learning_rate": 2.1158714431082937e-05, "loss": 0.3143, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.5284844565529083, "learning_rate": 2.110225054402733e-05, "loss": 0.2682, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.5512125481891051, "learning_rate": 2.1045777843405747e-05, "loss": 0.3116, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.5714637932168637, "learning_rate": 2.09892967807724e-05, "loss": 0.3095, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.5347514575103565, "learning_rate": 2.093280780774835e-05, "loss": 0.3088, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.6222965983720251, "learning_rate": 2.087631137601793e-05, "loss": 0.3258, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.922658805675728, "learning_rate": 2.0819807937325104e-05, "loss": 0.3591, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.4918766656051079, "learning_rate": 2.0763297943469847e-05, "loss": 0.4764, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.5342883774408672, "learning_rate": 2.070678184630458e-05, "loss": 0.2404, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.5855167166902595, "learning_rate": 2.06502600977305e-05, "loss": 0.2543, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.5047473863786791, "learning_rate": 2.0593733149694008e-05, "loss": 0.2798, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.504821977919847, "learning_rate": 2.0537201454183074e-05, "loss": 0.2695, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.6557985371424344, "learning_rate": 2.0480665463223626e-05, "loss": 0.3223, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.5356608314180761, "learning_rate": 2.042412562887594e-05, "loss": 0.2662, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.5403753461004601, "learning_rate": 2.0367582403231033e-05, "loss": 0.3322, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.5294202292708077, "learning_rate": 2.0311036238407023e-05, "loss": 0.3045, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.5647279376284552, "learning_rate": 2.0254487586545534e-05, "loss": 0.2944, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.5666397314243067, "learning_rate": 2.0197936899808088e-05, "loss": 0.3031, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.6102990410053588, "learning_rate": 2.0141384630372466e-05, "loss": 0.3645, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.5158064773543227, "learning_rate": 2.0084831230429106e-05, "loss": 0.3091, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.5736034769976597, "learning_rate": 2.0028277152177492e-05, "loss": 0.3122, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.6580173725535483, "learning_rate": 1.9971722847822518e-05, "loss": 0.3103, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.5500956226153523, "learning_rate": 1.99151687695709e-05, "loss": 0.3185, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.5501539886317446, "learning_rate": 1.9858615369627537e-05, "loss": 0.2628, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.5007137620057298, "learning_rate": 1.9802063100191916e-05, "loss": 0.2713, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.570941845070768, "learning_rate": 1.974551241345447e-05, "loss": 0.3045, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.5535454631916099, "learning_rate": 1.9688963761592984e-05, "loss": 0.2876, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.5005373874793833, "learning_rate": 1.963241759676897e-05, "loss": 0.2705, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.5619531847118553, "learning_rate": 1.9575874371124066e-05, "loss": 0.33, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.5466832959103446, "learning_rate": 1.951933453677638e-05, "loss": 0.3482, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.6025084559337656, "learning_rate": 1.9462798545816932e-05, "loss": 0.284, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.5947588303651664, "learning_rate": 1.9406266850305996e-05, "loss": 0.2873, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.4944936490162797, "learning_rate": 1.9349739902269503e-05, "loss": 0.292, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.6290648536101131, "learning_rate": 1.9293218153695425e-05, "loss": 0.2699, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.5841078213280237, "learning_rate": 1.9236702056530153e-05, "loss": 0.279, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.5356447777889676, "learning_rate": 1.9180192062674907e-05, "loss": 0.2789, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.5271270877997745, "learning_rate": 1.9123688623982076e-05, "loss": 0.2859, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.5124761935382275, "learning_rate": 1.906719219225165e-05, "loss": 0.4489, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.5114333289564948, "learning_rate": 1.9010703219227603e-05, "loss": 0.2974, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.5392597448292638, "learning_rate": 1.8954222156594256e-05, "loss": 0.2916, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.5627319761891648, "learning_rate": 1.8897749455972673e-05, "loss": 0.4165, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.508226954937701, "learning_rate": 1.884128556891707e-05, "loss": 0.2764, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.5187826585390135, "learning_rate": 1.878483094691119e-05, "loss": 0.2606, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.525271634426315, "learning_rate": 1.8728386041364664e-05, "loss": 0.3035, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.4879666421089113, "learning_rate": 1.867195130360947e-05, "loss": 0.3029, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.4997022109164738, "learning_rate": 1.8615527184896263e-05, "loss": 0.2873, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.5623400639188203, "learning_rate": 1.8559114136390795e-05, "loss": 0.2654, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.5262659979808203, "learning_rate": 1.8502712609170298e-05, "loss": 0.2826, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.5515958154611227, "learning_rate": 1.8446323054219876e-05, "loss": 0.3063, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.566007731256886, "learning_rate": 1.838994592242891e-05, "loss": 0.3057, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.47288660364860224, "learning_rate": 1.8333581664587453e-05, "loss": 0.3283, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.5421439668042417, "learning_rate": 1.8277230731382593e-05, "loss": 0.2978, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.5901449817149077, "learning_rate": 1.82208935733949e-05, "loss": 0.3077, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.535373234298543, "learning_rate": 1.8164570641094793e-05, "loss": 0.3043, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.5702083027629863, "learning_rate": 1.810826238483892e-05, "loss": 0.2764, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.5013375015017625, "learning_rate": 1.8051969254866608e-05, "loss": 0.3022, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.5406032811959521, "learning_rate": 1.7995691701296226e-05, "loss": 0.3007, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.5693196990919734, "learning_rate": 1.7939430174121593e-05, "loss": 0.2993, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.5623995993881015, "learning_rate": 1.788318512320838e-05, "loss": 0.3181, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.5900218024611547, "learning_rate": 1.782695699829051e-05, "loss": 0.2998, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.518108370686392, "learning_rate": 1.7770746248966587e-05, "loss": 0.2971, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.5580882779827867, "learning_rate": 1.7714553324696243e-05, "loss": 0.2876, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.5705781173746917, "learning_rate": 1.7658378674796614e-05, "loss": 0.264, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.6333298209390612, "learning_rate": 1.76022227484387e-05, "loss": 0.3391, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.5624803692422777, "learning_rate": 1.7546085994643807e-05, "loss": 0.3004, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.5513698746209525, "learning_rate": 1.7489968862279902e-05, "loss": 0.2962, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.5445978399499917, "learning_rate": 1.743387180005809e-05, "loss": 0.3003, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.567614114342049, "learning_rate": 1.737779525652899e-05, "loss": 0.285, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.5359911103178658, "learning_rate": 1.732173968007914e-05, "loss": 0.2834, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.5081867752682425, "learning_rate": 1.7265705518927437e-05, "loss": 0.2653, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.5668960639530399, "learning_rate": 1.7209693221121542e-05, "loss": 0.2781, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.5602618149674873, "learning_rate": 1.7153703234534302e-05, "loss": 0.2832, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.445096273379865, "learning_rate": 1.709773600686015e-05, "loss": 0.3289, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.5931804963837979, "learning_rate": 1.7041791985611548e-05, "loss": 0.315, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.5121399275305002, "learning_rate": 1.69858716181154e-05, "loss": 0.2963, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.6110237514668094, "learning_rate": 1.692997535150948e-05, "loss": 0.2928, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.5033790015152043, "learning_rate": 1.687410363273884e-05, "loss": 0.3096, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.49485972533476186, "learning_rate": 1.6818256908552257e-05, "loss": 0.2792, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.5081285580063645, "learning_rate": 1.6762435625498646e-05, "loss": 0.2889, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.5416252720262351, "learning_rate": 1.67066402299235e-05, "loss": 0.2565, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.535354326354648, "learning_rate": 1.6650871167965313e-05, "loss": 0.2968, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.5345502158699994, "learning_rate": 1.6595128885552028e-05, "loss": 0.2691, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.5304177427092092, "learning_rate": 1.653941382839745e-05, "loss": 0.261, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.509471645104731, "learning_rate": 1.6483726441997673e-05, "loss": 0.1519, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.4900423829905197, "learning_rate": 1.642806717162757e-05, "loss": 0.1703, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.4932193244049979, "learning_rate": 1.637243646233718e-05, "loss": 0.1768, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.49530691005269833, "learning_rate": 1.6316834758948174e-05, "loss": 0.2362, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.5472363867774077, "learning_rate": 1.6261262506050282e-05, "loss": 0.1577, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.5581414928700422, "learning_rate": 1.620572014799777e-05, "loss": 0.2095, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.49621685666434034, "learning_rate": 1.6150208128905857e-05, "loss": 0.2388, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.5287735326148103, "learning_rate": 1.6094726892647147e-05, "loss": 0.1593, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.5185280988654101, "learning_rate": 1.6039276882848135e-05, "loss": 0.1522, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.5321223128381928, "learning_rate": 1.5983858542885635e-05, "loss": 0.2219, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.5661748205166156, "learning_rate": 1.5928472315883203e-05, "loss": 0.1965, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.4798972585211819, "learning_rate": 1.5873118644707633e-05, "loss": 0.162, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.4406880181263564, "learning_rate": 1.5817797971965413e-05, "loss": 0.1589, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.4958666515569796, "learning_rate": 1.576251073999917e-05, "loss": 0.1919, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.48439340453521895, "learning_rate": 1.5707257390884126e-05, "loss": 0.1728, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.44835636475623414, "learning_rate": 1.5652038366424595e-05, "loss": 0.1627, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.5142931571881714, "learning_rate": 1.5596854108150424e-05, "loss": 0.1954, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.4712825538293911, "learning_rate": 1.5541705057313476e-05, "loss": 0.1738, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.49297098933205385, "learning_rate": 1.5486591654884086e-05, "loss": 0.172, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.4840009177292952, "learning_rate": 1.543151434154755e-05, "loss": 0.2009, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.4800694913681511, "learning_rate": 1.5376473557700615e-05, "loss": 0.1616, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.45078420559502436, "learning_rate": 1.5321469743447893e-05, "loss": 0.1676, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.4639896867640185, "learning_rate": 1.5266503338598434e-05, "loss": 0.1994, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.4812281396503706, "learning_rate": 1.5211574782662149e-05, "loss": 0.1787, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.4769937075192111, "learning_rate": 1.5156684514846307e-05, "loss": 0.2062, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.4493103395400834, "learning_rate": 1.5101832974052012e-05, "loss": 0.1828, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3774078108303738, "learning_rate": 1.5047020598870737e-05, "loss": 0.2053, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.42980506429417664, "learning_rate": 1.4992247827580778e-05, "loss": 0.1944, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.4953872538655371, "learning_rate": 1.493751509814374e-05, "loss": 0.1891, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.46010014709315655, "learning_rate": 1.4882822848201073e-05, "loss": 0.1817, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.4172346407319033, "learning_rate": 1.4828171515070553e-05, "loss": 0.2127, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.5593858217152753, "learning_rate": 1.4773561535742793e-05, "loss": 0.1772, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.4357676902119135, "learning_rate": 1.4718993346877715e-05, "loss": 0.355, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.5728283915613664, "learning_rate": 1.466446738480111e-05, "loss": 0.1729, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.47033657648052773, "learning_rate": 1.460998408550112e-05, "loss": 0.1795, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.46553501837110395, "learning_rate": 1.4555543884624751e-05, "loss": 0.1835, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.486188897962277, "learning_rate": 1.4501147217474402e-05, "loss": 0.1738, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.46704118039489656, "learning_rate": 1.444679451900437e-05, "loss": 0.1894, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.48582383658984696, "learning_rate": 1.4392486223817397e-05, "loss": 0.1424, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.42069704361995736, "learning_rate": 1.4338222766161143e-05, "loss": 0.1765, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.4087010241033719, "learning_rate": 1.4284004579924777e-05, "loss": 0.1744, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.4525257193574014, "learning_rate": 1.4229832098635479e-05, "loss": 0.2334, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.47854723536873145, "learning_rate": 1.4175705755454963e-05, "loss": 0.1694, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.44209169715633173, "learning_rate": 1.412162598317602e-05, "loss": 0.2274, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.4720011438487561, "learning_rate": 1.406759321421907e-05, "loss": 0.172, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.4747939418768313, "learning_rate": 1.401360788062871e-05, "loss": 0.1683, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.46797197905020316, "learning_rate": 1.3959670414070204e-05, "loss": 0.2195, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.4182698312942461, "learning_rate": 1.3905781245826108e-05, "loss": 0.2009, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.5038058674655868, "learning_rate": 1.3851940806792778e-05, "loss": 0.2896, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.4369409069622403, "learning_rate": 1.379814952747693e-05, "loss": 0.1616, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.45070744530519097, "learning_rate": 1.3744407837992193e-05, "loss": 0.1784, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.4577823909142851, "learning_rate": 1.3690716168055692e-05, "loss": 0.191, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.43829240704590283, "learning_rate": 1.363707494698459e-05, "loss": 0.1916, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.4740734579053017, "learning_rate": 1.358348460369265e-05, "loss": 0.2055, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.4816733648074758, "learning_rate": 1.352994556668684e-05, "loss": 0.1537, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.4588837834361728, "learning_rate": 1.3476458264063865e-05, "loss": 0.1749, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.5021220444675554, "learning_rate": 1.342302312350678e-05, "loss": 0.2183, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.48900828004800434, "learning_rate": 1.3369640572281537e-05, "loss": 0.235, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.4442074042488406, "learning_rate": 1.3316311037233596e-05, "loss": 0.1679, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.5071613694359346, "learning_rate": 1.326303494478451e-05, "loss": 0.2488, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.4553437213796253, "learning_rate": 1.3209812720928472e-05, "loss": 0.1735, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.47131891237273604, "learning_rate": 1.315664479122898e-05, "loss": 0.1977, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.4494585843059059, "learning_rate": 1.3103531580815378e-05, "loss": 0.2133, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.5004195314685207, "learning_rate": 1.3050473514379488e-05, "loss": 0.1809, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.549866280088875, "learning_rate": 1.2997471016172188e-05, "loss": 0.2106, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.5063418345626568, "learning_rate": 1.2944524510000042e-05, "loss": 0.214, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.4393029525018521, "learning_rate": 1.2891634419221908e-05, "loss": 0.2842, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.7690450150845995, "learning_rate": 1.2838801166745545e-05, "loss": 0.1853, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.4652313864336921, "learning_rate": 1.2786025175024216e-05, "loss": 0.1643, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.4377099227809979, "learning_rate": 1.2733306866053357e-05, "loss": 0.2277, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.5723874070187797, "learning_rate": 1.2680646661367163e-05, "loss": 0.1783, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.46074459992109906, "learning_rate": 1.2628044982035219e-05, "loss": 0.1849, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.5171918302405922, "learning_rate": 1.2575502248659155e-05, "loss": 0.3651, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.40757787240564536, "learning_rate": 1.2523018881369269e-05, "loss": 0.1979, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.5591224707995647, "learning_rate": 1.2470595299821176e-05, "loss": 0.1828, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.4353583466861661, "learning_rate": 1.2418231923192416e-05, "loss": 0.182, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.44869787574432274, "learning_rate": 1.2365929170179165e-05, "loss": 0.2, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.45443832887088453, "learning_rate": 1.2313687458992848e-05, "loss": 0.1908, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.42316501626961317, "learning_rate": 1.2261507207356785e-05, "loss": 0.1522, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.49300882756691483, "learning_rate": 1.220938883250288e-05, "loss": 0.1431, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.45333555233019773, "learning_rate": 1.215733275116827e-05, "loss": 0.1694, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.49310160394928876, "learning_rate": 1.2105339379592005e-05, "loss": 0.2326, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.5201093444182371, "learning_rate": 1.2053409133511681e-05, "loss": 0.1938, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.4980793281616057, "learning_rate": 1.2001542428160173e-05, "loss": 0.2909, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.42896779112269573, "learning_rate": 1.1949739678262278e-05, "loss": 0.1777, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.41734913894866316, "learning_rate": 1.189800129803139e-05, "loss": 0.1516, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.44464559318174446, "learning_rate": 1.1846327701166228e-05, "loss": 0.1623, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.43774481314228686, "learning_rate": 1.1794719300847493e-05, "loss": 0.2223, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.4459439430729495, "learning_rate": 1.1743176509734582e-05, "loss": 0.2002, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.52310492620312, "learning_rate": 1.1691699739962275e-05, "loss": 0.3404, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.5321210569786522, "learning_rate": 1.1640289403137456e-05, "loss": 0.1796, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.4133585746694392, "learning_rate": 1.1588945910335802e-05, "loss": 0.1835, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.45668833629820804, "learning_rate": 1.1537669672098517e-05, "loss": 0.2315, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.45702923888867353, "learning_rate": 1.1486461098429036e-05, "loss": 0.162, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.4138301233279607, "learning_rate": 1.1435320598789747e-05, "loss": 0.1676, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.5349941108234407, "learning_rate": 1.1384248582098736e-05, "loss": 0.1891, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.5499614735326298, "learning_rate": 1.1333245456726467e-05, "loss": 0.1682, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.4406785566621523, "learning_rate": 1.128231163049258e-05, "loss": 0.1545, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.4976508673880257, "learning_rate": 1.123144751066259e-05, "loss": 0.2022, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.46327604621683516, "learning_rate": 1.1180653503944657e-05, "loss": 0.1574, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.43930939406587155, "learning_rate": 1.1129930016486287e-05, "loss": 0.1952, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.4319239251921424, "learning_rate": 1.107927745387114e-05, "loss": 0.1996, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.45604732637047285, "learning_rate": 1.1028696221115766e-05, "loss": 0.2019, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.439829464956197, "learning_rate": 1.0978186722666341e-05, "loss": 0.1951, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.4530717225693778, "learning_rate": 1.0927749362395475e-05, "loss": 0.1841, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.45740615404872403, "learning_rate": 1.0877384543598954e-05, "loss": 0.214, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.47330616667043285, "learning_rate": 1.0827092668992529e-05, "loss": 0.208, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.4517702572302499, "learning_rate": 1.077687414070869e-05, "loss": 0.1834, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.38506917435720817, "learning_rate": 1.0726729360293451e-05, "loss": 0.1827, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.4287659992641278, "learning_rate": 1.0676658728703147e-05, "loss": 0.1962, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.5475564862934833, "learning_rate": 1.0626662646301198e-05, "loss": 0.1645, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.46135181515890833, "learning_rate": 1.0576741512854958e-05, "loss": 0.198, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.5333814462443977, "learning_rate": 1.052689572753247e-05, "loss": 0.214, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.39707668919210476, "learning_rate": 1.0477125688899328e-05, "loss": 0.1343, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.42902823000212, "learning_rate": 1.0427431794915406e-05, "loss": 0.1872, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.4495141656505294, "learning_rate": 1.0377814442931769e-05, "loss": 0.1603, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.45691725336497907, "learning_rate": 1.0328274029687439e-05, "loss": 0.1969, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.46192224759618217, "learning_rate": 1.0278810951306253e-05, "loss": 0.1967, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.4569656187533115, "learning_rate": 1.0229425603293647e-05, "loss": 0.2117, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.521998524624734, "learning_rate": 1.0180118380533558e-05, "loss": 0.2735, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.4275678625131023, "learning_rate": 1.0130889677285225e-05, "loss": 0.2304, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.43748336231813867, "learning_rate": 1.008173988718005e-05, "loss": 0.1528, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.47029720319885104, "learning_rate": 1.0032669403218439e-05, "loss": 0.1903, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.509104381590983, "learning_rate": 9.983678617766677e-06, "loss": 0.1829, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.43685277847468895, "learning_rate": 9.934767922553788e-06, "loss": 0.2124, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.48822629668932926, "learning_rate": 9.885937708668371e-06, "loss": 0.1832, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.4360626392288573, "learning_rate": 9.837188366555524e-06, "loss": 0.1849, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.45859229844575894, "learning_rate": 9.788520286013691e-06, "loss": 0.1382, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.4244885479918171, "learning_rate": 9.739933856191537e-06, "loss": 0.1921, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.46126672698154664, "learning_rate": 9.691429465584866e-06, "loss": 0.2882, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.42733467458123603, "learning_rate": 9.643007502033492e-06, "loss": 0.2007, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.5223883198121629, "learning_rate": 9.594668352718152e-06, "loss": 0.1738, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.5125291458961545, "learning_rate": 9.546412404157383e-06, "loss": 0.1875, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.5707166114460264, "learning_rate": 9.498240042204471e-06, "loss": 0.3109, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.5564711375266008, "learning_rate": 9.450151652044339e-06, "loss": 0.2176, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.543871798701335, "learning_rate": 9.402147618190472e-06, "loss": 0.1906, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.4627858889263295, "learning_rate": 9.354228324481841e-06, "loss": 0.157, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.3795217119238839, "learning_rate": 9.306394154079852e-06, "loss": 0.3217, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.4438176064143049, "learning_rate": 9.258645489465254e-06, "loss": 0.2387, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.44712149484074204, "learning_rate": 9.21098271243509e-06, "loss": 0.2561, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.5171023828646418, "learning_rate": 9.163406204099659e-06, "loss": 0.1735, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.41982424776063704, "learning_rate": 9.115916344879452e-06, "loss": 0.1879, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.4915623902198705, "learning_rate": 9.068513514502126e-06, "loss": 0.1805, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.4493159034777753, "learning_rate": 9.021198091999439e-06, "loss": 0.2234, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.4533465246685413, "learning_rate": 8.973970455704251e-06, "loss": 0.1749, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.4291582963899051, "learning_rate": 8.926830983247495e-06, "loss": 0.2068, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.4303716173827569, "learning_rate": 8.879780051555116e-06, "loss": 0.1534, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.4583991821950341, "learning_rate": 8.83281803684512e-06, "loss": 0.2155, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.4743973508833468, "learning_rate": 8.785945314624532e-06, "loss": 0.1588, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.5875354918654506, "learning_rate": 8.739162259686385e-06, "loss": 0.1935, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.41393486402579277, "learning_rate": 8.692469246106734e-06, "loss": 0.1749, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.4667989250428628, "learning_rate": 8.645866647241677e-06, "loss": 0.1929, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.42897996912027847, "learning_rate": 8.599354835724348e-06, "loss": 0.2251, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.44945066641840126, "learning_rate": 8.552934183461958e-06, "loss": 0.1953, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.41759864501070426, "learning_rate": 8.506605061632805e-06, "loss": 0.1945, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.47467889423547227, "learning_rate": 8.460367840683308e-06, "loss": 0.2272, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.4950818562553163, "learning_rate": 8.414222890325065e-06, "loss": 0.1867, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.4801994095288517, "learning_rate": 8.368170579531855e-06, "loss": 0.2596, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.43707184534395405, "learning_rate": 8.322211276536733e-06, "loss": 0.1841, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.46773712786940974, "learning_rate": 8.27634534882907e-06, "loss": 0.3133, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.4490830262046798, "learning_rate": 8.230573163151585e-06, "loss": 0.1421, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.5787196186058939, "learning_rate": 8.184895085497466e-06, "loss": 0.1847, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.5200343310421797, "learning_rate": 8.139311481107401e-06, "loss": 0.1905, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.45982252728618417, "learning_rate": 8.093822714466686e-06, "loss": 0.3037, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.44473645371161125, "learning_rate": 8.048429149302271e-06, "loss": 0.1876, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.4741802253566823, "learning_rate": 8.003131148579902e-06, "loss": 0.2069, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.41123005882383573, "learning_rate": 7.957929074501182e-06, "loss": 0.1753, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.4709666748726915, "learning_rate": 7.912823288500695e-06, "loss": 0.1583, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.4150777531358171, "learning_rate": 7.867814151243102e-06, "loss": 0.1576, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.4602957482402597, "learning_rate": 7.822902022620267e-06, "loss": 0.1987, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.47631343552723465, "learning_rate": 7.778087261748377e-06, "loss": 0.1895, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.43532937598573745, "learning_rate": 7.733370226965056e-06, "loss": 0.1628, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.4300205186671311, "learning_rate": 7.688751275826527e-06, "loss": 0.1752, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.47417758487343864, "learning_rate": 7.644230765104735e-06, "loss": 0.1389, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.40854579048473394, "learning_rate": 7.599809050784502e-06, "loss": 0.1681, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.40920979702966404, "learning_rate": 7.555486488060661e-06, "loss": 0.1699, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.42733141462893875, "learning_rate": 7.511263431335249e-06, "loss": 0.2008, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.4892001306126981, "learning_rate": 7.467140234214656e-06, "loss": 0.1728, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.43365651995743665, "learning_rate": 7.423117249506777e-06, "loss": 0.1434, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.477497379862911, "learning_rate": 7.379194829218231e-06, "loss": 0.2066, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.39693646898202095, "learning_rate": 7.335373324551518e-06, "loss": 0.19, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.45012621918673595, "learning_rate": 7.291653085902224e-06, "loss": 0.1776, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.46593102513136003, "learning_rate": 7.248034462856213e-06, "loss": 0.1779, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.4484309945392291, "learning_rate": 7.20451780418683e-06, "loss": 0.1876, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.4558480406148442, "learning_rate": 7.161103457852128e-06, "loss": 0.1483, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.48584926688479163, "learning_rate": 7.117791770992046e-06, "loss": 0.1909, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.41968119213282845, "learning_rate": 7.074583089925688e-06, "loss": 0.2059, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.49245995803896814, "learning_rate": 7.0314777601485155e-06, "loss": 0.1898, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.44805497581430964, "learning_rate": 6.988476126329604e-06, "loss": 0.1999, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.45289985011585393, "learning_rate": 6.945578532308857e-06, "loss": 0.194, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.38773663042214795, "learning_rate": 6.902785321094301e-06, "loss": 0.1702, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.4711012810375585, "learning_rate": 6.8600968348593115e-06, "loss": 0.2309, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.4335945023521458, "learning_rate": 6.817513414939892e-06, "loss": 0.2145, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.41061418667414373, "learning_rate": 6.775035401831924e-06, "loss": 0.1678, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.4530578137416507, "learning_rate": 6.732663135188473e-06, "loss": 0.1717, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.41359332897876316, "learning_rate": 6.690396953817055e-06, "loss": 0.2271, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.403059491586281, "learning_rate": 6.648237195676927e-06, "loss": 0.1529, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.4443721779062726, "learning_rate": 6.606184197876395e-06, "loss": 0.1772, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.46559787445332185, "learning_rate": 6.564238296670109e-06, "loss": 0.1893, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.4628700017797117, "learning_rate": 6.52239982745638e-06, "loss": 0.1915, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.43892463712125845, "learning_rate": 6.480669124774484e-06, "loss": 0.2018, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.5382848745362127, "learning_rate": 6.439046522302013e-06, "loss": 0.207, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.5241230028607481, "learning_rate": 6.397532352852191e-06, "loss": 0.1829, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.47085664655135323, "learning_rate": 6.356126948371202e-06, "loss": 0.2089, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.44267934273935466, "learning_rate": 6.314830639935559e-06, "loss": 0.1959, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.4776937140642282, "learning_rate": 6.273643757749448e-06, "loss": 0.1698, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.44858130258074946, "learning_rate": 6.2325666311420856e-06, "loss": 0.1733, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.47535944188341944, "learning_rate": 6.1915995885650675e-06, "loss": 0.1852, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.4013664324492993, "learning_rate": 6.150742957589784e-06, "loss": 0.1854, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.43848922427906173, "learning_rate": 6.109997064904774e-06, "loss": 0.2268, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.4099092512346715, "learning_rate": 6.069362236313092e-06, "loss": 0.1682, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.4481869822645809, "learning_rate": 6.0288387967297565e-06, "loss": 0.1438, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.4407812901295227, "learning_rate": 5.988427070179108e-06, "loss": 0.162, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.43600720114962693, "learning_rate": 5.948127379792234e-06, "loss": 0.1702, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.4744846279779204, "learning_rate": 5.90794004780439e-06, "loss": 0.1524, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.5035593928937413, "learning_rate": 5.867865395552405e-06, "loss": 0.1708, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.48386226062592735, "learning_rate": 5.8279037434721364e-06, "loss": 0.1816, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.43914984771651433, "learning_rate": 5.788055411095892e-06, "loss": 0.1619, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.5187730005296158, "learning_rate": 5.7483207170498625e-06, "loss": 0.2578, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.44152327646175354, "learning_rate": 5.708699979051613e-06, "loss": 0.1477, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.4094091989127655, "learning_rate": 5.66919351390751e-06, "loss": 0.1824, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.5131559355692736, "learning_rate": 5.629801637510188e-06, "loss": 0.185, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.49150875044737347, "learning_rate": 5.590524664836043e-06, "loss": 0.1557, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.425852339468311, "learning_rate": 5.551362909942708e-06, "loss": 0.1868, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.45461062227082155, "learning_rate": 5.51231668596653e-06, "loss": 0.1778, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.4430038385220367, "learning_rate": 5.47338630512007e-06, "loss": 0.1724, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.4382526005907604, "learning_rate": 5.434572078689617e-06, "loss": 0.1841, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.4211513627099975, "learning_rate": 5.395874317032694e-06, "loss": 0.1686, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.48910192746589193, "learning_rate": 5.357293329575573e-06, "loss": 0.1252, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.4113096462564557, "learning_rate": 5.318829424810797e-06, "loss": 0.2218, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.4094519954286364, "learning_rate": 5.280482910294728e-06, "loss": 0.1655, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.409764446332396, "learning_rate": 5.242254092645078e-06, "loss": 0.1735, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.4333531096151662, "learning_rate": 5.2041432775384445e-06, "loss": 0.1533, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.42509440066908133, "learning_rate": 5.166150769707892e-06, "loss": 0.1406, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.4307672458305016, "learning_rate": 5.128276872940503e-06, "loss": 0.2164, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.45873869766509157, "learning_rate": 5.090521890074953e-06, "loss": 0.1719, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.4153393903574722, "learning_rate": 5.0528861229990675e-06, "loss": 0.1958, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.44121257531130764, "learning_rate": 5.015369872647442e-06, "loss": 0.1178, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.4318770426039556, "learning_rate": 4.9779734389990195e-06, "loss": 0.1335, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.5540413590223551, "learning_rate": 4.940697121074675e-06, "loss": 0.3224, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.45672966981254576, "learning_rate": 4.903541216934864e-06, "loss": 0.1625, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.4653656435936646, "learning_rate": 4.8665060236772e-06, "loss": 0.2164, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.4932511374775009, "learning_rate": 4.829591837434102e-06, "loss": 0.2079, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.42601017466595215, "learning_rate": 4.792798953370424e-06, "loss": 0.1889, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.5083402461011608, "learning_rate": 4.756127665681083e-06, "loss": 0.1905, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.7439308638901584, "learning_rate": 4.719578267588725e-06, "loss": 0.1831, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.4890263621988832, "learning_rate": 4.6831510513413525e-06, "loss": 0.1229, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4732441128740971, "learning_rate": 4.6468463082100176e-06, "loss": 0.1189, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.42050238752200647, "learning_rate": 4.610664328486485e-06, "loss": 0.1651, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.349622303313759, "learning_rate": 4.5746054014809e-06, "loss": 0.1508, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.3876866100222178, "learning_rate": 4.5386698155194766e-06, "loss": 0.0958, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3200920392778899, "learning_rate": 4.502857857942204e-06, "loss": 0.1272, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.37111092862722783, "learning_rate": 4.467169815100549e-06, "loss": 0.1191, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.37194261275341517, "learning_rate": 4.431605972355137e-06, "loss": 0.0977, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.41619937348095654, "learning_rate": 4.396166614073516e-06, "loss": 0.1386, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.46786744368643296, "learning_rate": 4.360852023627846e-06, "loss": 0.1354, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.4660023147878886, "learning_rate": 4.325662483392656e-06, "loss": 0.1417, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.3985034244647334, "learning_rate": 4.29059827474257e-06, "loss": 0.1006, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.34382991873102486, "learning_rate": 4.255659678050063e-06, "loss": 0.0934, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.3709102597376672, "learning_rate": 4.22084697268323e-06, "loss": 0.0795, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.3761369741324875, "learning_rate": 4.186160437003535e-06, "loss": 0.1227, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.4223442506392429, "learning_rate": 4.151600348363582e-06, "loss": 0.1326, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.39832394247942754, "learning_rate": 4.11716698310493e-06, "loss": 0.0955, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.41404951952696434, "learning_rate": 4.082860616555848e-06, "loss": 0.1484, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.3626261257478101, "learning_rate": 4.048681523029125e-06, "loss": 0.16, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.36752399914854483, "learning_rate": 4.014629975819882e-06, "loss": 0.1128, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.428964208315688, "learning_rate": 3.9807062472033855e-06, "loss": 0.1175, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.38882750723185405, "learning_rate": 3.94691060843287e-06, "loss": 0.1364, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.4097858985297608, "learning_rate": 3.913243329737353e-06, "loss": 0.1518, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.4248896866547486, "learning_rate": 3.879704680319503e-06, "loss": 0.1292, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.46651104769060864, "learning_rate": 3.846294928353471e-06, "loss": 0.1335, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.4077049860839382, "learning_rate": 3.8130143409827345e-06, "loss": 0.1135, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.4012369518040361, "learning_rate": 3.7798631843179887e-06, "loss": 0.1383, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.38512478135924016, "learning_rate": 3.7468417234349973e-06, "loss": 0.281, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.33385855285915095, "learning_rate": 3.7139502223724823e-06, "loss": 0.1375, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.3854394609103303, "learning_rate": 3.6811889441300095e-06, "loss": 0.1349, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.37167813882126594, "learning_rate": 3.648558150665886e-06, "loss": 0.1343, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.3240627218504701, "learning_rate": 3.616058102895075e-06, "loss": 0.1016, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.3880598441632043, "learning_rate": 3.583689060687079e-06, "loss": 0.1445, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.330374145190745, "learning_rate": 3.5514512828639023e-06, "loss": 0.137, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.35549990718998015, "learning_rate": 3.51934502719796e-06, "loss": 0.132, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.3573833469530966, "learning_rate": 3.4873705504100185e-06, "loss": 0.2186, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.4012082800561019, "learning_rate": 3.4555281081671345e-06, "loss": 0.1294, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.33376921454620706, "learning_rate": 3.4238179550806326e-06, "loss": 0.0914, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.3435486153440405, "learning_rate": 3.3922403447040497e-06, "loss": 0.0924, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.35243205967388297, "learning_rate": 3.3607955295311247e-06, "loss": 0.2127, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.4633388727445453, "learning_rate": 3.32948376099375e-06, "loss": 0.1346, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.4820190060682156, "learning_rate": 3.2983052894599976e-06, "loss": 0.1024, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.3377876424440467, "learning_rate": 3.2672603642320945e-06, "loss": 0.1458, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.36247699826178476, "learning_rate": 3.236349233544438e-06, "loss": 0.1135, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.34896444348194605, "learning_rate": 3.205572144561604e-06, "loss": 0.1854, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.3433132231954667, "learning_rate": 3.174929343376374e-06, "loss": 0.1507, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.35597386362393907, "learning_rate": 3.1444210750077777e-06, "loss": 0.1042, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.34322013556426717, "learning_rate": 3.1140475833991046e-06, "loss": 0.0981, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.3942045035851495, "learning_rate": 3.0838091114159895e-06, "loss": 0.1376, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.3488547574585174, "learning_rate": 3.0537059008444524e-06, "loss": 0.1429, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.41955738722442615, "learning_rate": 3.0237381923889563e-06, "loss": 0.1417, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.35172534724075183, "learning_rate": 2.9939062256704997e-06, "loss": 0.1269, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.36077689669772384, "learning_rate": 2.964210239224696e-06, "loss": 0.1155, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.39539715637360084, "learning_rate": 2.934650470499869e-06, "loss": 0.1235, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.3863963132259396, "learning_rate": 2.905227155855128e-06, "loss": 0.2207, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.3642692792406256, "learning_rate": 2.875940530558519e-06, "loss": 0.1308, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.380376095369995, "learning_rate": 2.8467908287851154e-06, "loss": 0.1817, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.3607037564245957, "learning_rate": 2.8177782836151603e-06, "loss": 0.1378, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.3288798809628441, "learning_rate": 2.7889031270321874e-06, "loss": 0.1173, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.34825530147235856, "learning_rate": 2.760165589921184e-06, "loss": 0.1537, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.3270937558049105, "learning_rate": 2.7315659020667305e-06, "loss": 0.157, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.34719435685331895, "learning_rate": 2.703104292151164e-06, "loss": 0.1577, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.3356030248699747, "learning_rate": 2.6747809877527607e-06, "loss": 0.1253, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 3.2083209100457246, "learning_rate": 2.6465962153439082e-06, "loss": 0.1688, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.3738473390127509, "learning_rate": 2.618550200289303e-06, "loss": 0.1041, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.34647260171286137, "learning_rate": 2.59064316684412e-06, "loss": 0.1165, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.32967179116954326, "learning_rate": 2.562875338152264e-06, "loss": 0.1152, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.3541963969165611, "learning_rate": 2.5352469362445552e-06, "loss": 0.1427, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.3534555843191611, "learning_rate": 2.5077581820369523e-06, "loss": 0.1228, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.37314501748495993, "learning_rate": 2.480409295328803e-06, "loss": 0.0945, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.3606737714010255, "learning_rate": 2.45320049480108e-06, "loss": 0.2747, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.35986929508793203, "learning_rate": 2.4261319980146293e-06, "loss": 0.1182, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.3490981427785689, "learning_rate": 2.399204021408421e-06, "loss": 0.1281, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.3759075167338118, "learning_rate": 2.3724167802978395e-06, "loss": 0.1326, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.3828515970216181, "learning_rate": 2.3457704888729625e-06, "loss": 0.1353, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.35767711370899447, "learning_rate": 2.3192653601968162e-06, "loss": 0.1245, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.33444228804313436, "learning_rate": 2.2929016062037057e-06, "loss": 0.0993, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.32576126390116356, "learning_rate": 2.2666794376975055e-06, "loss": 0.1251, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.35786782212404067, "learning_rate": 2.24059906434998e-06, "loss": 0.1453, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.42921268383073297, "learning_rate": 2.214660694699091e-06, "loss": 0.2184, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.38655428795165026, "learning_rate": 2.188864536147355e-06, "loss": 0.1168, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.3660169183380546, "learning_rate": 2.1632107949601757e-06, "loss": 0.1056, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.3645218795756303, "learning_rate": 2.137699676264171e-06, "loss": 0.1442, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.40669573137216414, "learning_rate": 2.1123313840455738e-06, "loss": 0.1344, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.3358908692862493, "learning_rate": 2.08710612114857e-06, "loss": 0.093, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.5750373898841402, "learning_rate": 2.0620240892736953e-06, "loss": 0.1376, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.35004503800690656, "learning_rate": 2.0370854889762e-06, "loss": 0.0895, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.3668318747042285, "learning_rate": 2.0122905196644726e-06, "loss": 0.0882, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.34830418877544733, "learning_rate": 1.987639379598427e-06, "loss": 0.075, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.38281327925303305, "learning_rate": 1.963132265887919e-06, "loss": 0.136, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.3431026625217276, "learning_rate": 1.9387693744911784e-06, "loss": 0.1181, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.35439791996892744, "learning_rate": 1.9145509002132368e-06, "loss": 0.1049, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.3397748073198414, "learning_rate": 1.8904770367043723e-06, "loss": 0.1154, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.32756358109184003, "learning_rate": 1.8665479764585504e-06, "loss": 0.112, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.3510209434914568, "learning_rate": 1.8427639108118977e-06, "loss": 0.1097, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.3194796883522115, "learning_rate": 1.8191250299411755e-06, "loss": 0.1042, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.31869741412914504, "learning_rate": 1.7956315228622446e-06, "loss": 0.1042, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.3718515344042847, "learning_rate": 1.7722835774285553e-06, "loss": 0.0961, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.4583131811391708, "learning_rate": 1.7490813803296624e-06, "loss": 0.2089, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.33163027991497657, "learning_rate": 1.726025117089718e-06, "loss": 0.1121, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.4080513231180925, "learning_rate": 1.70311497206598e-06, "loss": 0.111, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.6923040725078672, "learning_rate": 1.6803511284473638e-06, "loss": 0.1143, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.36683296577444374, "learning_rate": 1.6577337682529538e-06, "loss": 0.1476, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.3821871346047465, "learning_rate": 1.6352630723305617e-06, "loss": 0.1318, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.3546949832295545, "learning_rate": 1.612939220355272e-06, "loss": 0.1545, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.35810760419635135, "learning_rate": 1.5907623908280112e-06, "loss": 0.126, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.35485412295341856, "learning_rate": 1.568732761074121e-06, "loss": 0.1326, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.40405026438064817, "learning_rate": 1.5468505072419237e-06, "loss": 0.1873, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.37244019205633366, "learning_rate": 1.5251158043013448e-06, "loss": 0.1457, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 1.2136791398650055, "learning_rate": 1.5035288260424885e-06, "loss": 0.0968, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.3567295981459111, "learning_rate": 1.4820897450742623e-06, "loss": 0.1191, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.364620260254549, "learning_rate": 1.4607987328229767e-06, "loss": 0.1259, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.37609824238176265, "learning_rate": 1.4396559595310056e-06, "loss": 0.1663, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.36080967193309416, "learning_rate": 1.4186615942553973e-06, "loss": 0.1199, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.3685640101520118, "learning_rate": 1.3978158048665424e-06, "loss": 0.1426, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.3562173336096619, "learning_rate": 1.3771187580468115e-06, "loss": 0.1241, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.38253370970341827, "learning_rate": 1.3565706192892392e-06, "loss": 0.1543, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.3289176971693305, "learning_rate": 1.3361715528961993e-06, "loss": 0.134, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.3840759824824583, "learning_rate": 1.3159217219780817e-06, "loss": 0.1279, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.3489538294533449, "learning_rate": 1.2958212884519949e-06, "loss": 0.0934, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.4354673964873783, "learning_rate": 1.2758704130404675e-06, "loss": 0.1106, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.3539626094370957, "learning_rate": 1.2560692552701738e-06, "loss": 0.1253, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.34196918169377605, "learning_rate": 1.2364179734706382e-06, "loss": 0.142, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.32916195865698766, "learning_rate": 1.2169167247729852e-06, "loss": 0.1236, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.39434279826080587, "learning_rate": 1.1975656651086864e-06, "loss": 0.1255, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.409282141407889, "learning_rate": 1.1783649492082926e-06, "loss": 0.2199, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.37849888930747577, "learning_rate": 1.1593147306002183e-06, "loss": 0.0905, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.34991029967439846, "learning_rate": 1.140415161609505e-06, "loss": 0.1293, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.39408402814701066, "learning_rate": 1.121666393356604e-06, "loss": 0.1322, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.399668446022798, "learning_rate": 1.1030685757561632e-06, "loss": 0.2048, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.3583755599290718, "learning_rate": 1.0846218575158373e-06, "loss": 0.1098, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.3435063597867605, "learning_rate": 1.066326386135097e-06, "loss": 0.1195, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.33543120097180296, "learning_rate": 1.0481823079040398e-06, "loss": 0.107, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.3475985955465829, "learning_rate": 1.0301897679022344e-06, "loss": 0.1347, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.3463192047805578, "learning_rate": 1.0123489099975491e-06, "loss": 0.1148, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.3413085875877828, "learning_rate": 9.9465987684501e-07, "loss": 0.1311, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.36294121468793494, "learning_rate": 9.771228098856534e-07, "loss": 0.1296, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.3568248816998758, "learning_rate": 9.597378493454013e-07, "loss": 0.1596, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.31683110329334796, "learning_rate": 9.425051342339353e-07, "loss": 0.1194, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.3815089330302614, "learning_rate": 9.254248023435864e-07, "loss": 0.0982, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.37171041605525884, "learning_rate": 9.084969902482288e-07, "loss": 0.1178, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.3679882800284726, "learning_rate": 8.917218333021993e-07, "loss": 0.1431, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.3526203004800434, "learning_rate": 8.750994656392109e-07, "loss": 0.3206, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.39323677269253776, "learning_rate": 8.58630020171265e-07, "loss": 0.1022, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.3832948711717346, "learning_rate": 8.423136285876099e-07, "loss": 0.1515, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.38242777358202, "learning_rate": 8.26150421353682e-07, "loss": 0.091, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.3579560432415831, "learning_rate": 8.101405277100549e-07, "loss": 0.1143, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.3546387079015238, "learning_rate": 7.942840756714077e-07, "loss": 0.1448, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.32465405948169673, "learning_rate": 7.785811920255093e-07, "loss": 0.1039, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.3229374589702056, "learning_rate": 7.630320023322024e-07, "loss": 0.1463, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.35180977998659146, "learning_rate": 7.476366309223903e-07, "loss": 0.154, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.6158267056170493, "learning_rate": 7.323952008970537e-07, "loss": 0.1462, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.3389396472894025, "learning_rate": 7.173078341262618e-07, "loss": 0.1281, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.31540579520121115, "learning_rate": 7.023746512481989e-07, "loss": 0.1305, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.4174280782253291, "learning_rate": 6.875957716681902e-07, "loss": 0.1337, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.3867912036872985, "learning_rate": 6.729713135577687e-07, "loss": 0.1146, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.36308465620691177, "learning_rate": 6.585013938537143e-07, "loss": 0.1723, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.36982384899154264, "learning_rate": 6.441861282571115e-07, "loss": 0.1201, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.35745291814713037, "learning_rate": 6.300256312324471e-07, "loss": 0.1494, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.32586193129790253, "learning_rate": 6.160200160066776e-07, "loss": 0.1218, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.34698443127590084, "learning_rate": 6.021693945683327e-07, "loss": 0.1743, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.36123270987393336, "learning_rate": 5.884738776666044e-07, "loss": 0.1188, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.33853524794406825, "learning_rate": 5.749335748104878e-07, "loss": 0.098, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.38595736805665626, "learning_rate": 5.615485942678778e-07, "loss": 0.1296, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.36329444953928636, "learning_rate": 5.483190430647289e-07, "loss": 0.1311, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.39292853102832387, "learning_rate": 5.352450269841747e-07, "loss": 0.1373, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.34356765144231727, "learning_rate": 5.22326650565701e-07, "loss": 0.1299, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.35890953224476985, "learning_rate": 5.095640171043048e-07, "loss": 0.1614, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.38004723508104177, "learning_rate": 4.969572286496594e-07, "loss": 0.1486, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.33354976865229863, "learning_rate": 4.845063860053079e-07, "loss": 0.1348, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.3398945177428492, "learning_rate": 4.7221158872785997e-07, "loss": 0.1199, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.34162050914097886, "learning_rate": 4.600729351261857e-07, "loss": 0.1322, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.32000215384827424, "learning_rate": 4.4809052226063355e-07, "loss": 0.1391, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.4196600014699592, "learning_rate": 4.3626444594226046e-07, "loss": 0.1584, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.41559620318191154, "learning_rate": 4.245948007320588e-07, "loss": 0.1161, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.3379227185923715, "learning_rate": 4.130816799401971e-07, "loss": 0.1554, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.3325709288115009, "learning_rate": 4.017251756252827e-07, "loss": 0.1236, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.3589713212421299, "learning_rate": 3.9052537859362473e-07, "loss": 0.1403, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.32712341609018625, "learning_rate": 3.7948237839849687e-07, "loss": 0.1374, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.33958293949717, "learning_rate": 3.6859626333943797e-07, "loss": 0.1304, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.3563880975523483, "learning_rate": 3.578671204615347e-07, "loss": 0.1373, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.415659630064091, "learning_rate": 3.472950355547267e-07, "loss": 0.2211, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.3251420184719307, "learning_rate": 3.3688009315312244e-07, "loss": 0.1173, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.3364814658210241, "learning_rate": 3.266223765343224e-07, "loss": 0.1347, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.3563406357429498, "learning_rate": 3.16521967718757e-07, "loss": 0.1292, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.33200134538195936, "learning_rate": 3.0657894746902726e-07, "loss": 0.1138, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.3222299881870608, "learning_rate": 2.9679339528925654e-07, "loss": 0.15, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.33804524696974403, "learning_rate": 2.871653894244597e-07, "loss": 0.0828, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.3820113590115317, "learning_rate": 2.7769500685991266e-07, "loss": 0.0956, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.3776183138045092, "learning_rate": 2.683823233205485e-07, "loss": 0.1317, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.37401625998452914, "learning_rate": 2.592274132703287e-07, "loss": 0.1322, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.36640252703633763, "learning_rate": 2.502303499116754e-07, "loss": 0.1326, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.36407506760842023, "learning_rate": 2.413912051848666e-07, "loss": 0.1073, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.3130016481822512, "learning_rate": 2.3271004976746613e-07, "loss": 0.1323, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.3250802021263835, "learning_rate": 2.2418695307376393e-07, "loss": 0.1203, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.33803909292656203, "learning_rate": 2.1582198325420968e-07, "loss": 0.1096, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.3264392504648582, "learning_rate": 2.0761520719488447e-07, "loss": 0.1098, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.37898166131862504, "learning_rate": 1.9956669051694798e-07, "loss": 0.1419, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.3565836386193667, "learning_rate": 1.916764975761254e-07, "loss": 0.1212, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.3611246927821769, "learning_rate": 1.839446914621923e-07, "loss": 0.1468, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.3384592853802618, "learning_rate": 1.7637133399845962e-07, "loss": 0.1331, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.3569751006084902, "learning_rate": 1.6895648574129397e-07, "loss": 0.3013, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.3353359376311823, "learning_rate": 1.6170020597962465e-07, "loss": 0.101, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.33659619800423596, "learning_rate": 1.5460255273447078e-07, "loss": 0.1556, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.3750328352037612, "learning_rate": 1.4766358275847715e-07, "loss": 0.0999, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.4002084828403259, "learning_rate": 1.4088335153546573e-07, "loss": 0.1333, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.3031557141800786, "learning_rate": 1.3426191327998496e-07, "loss": 0.1145, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.33247895940238814, "learning_rate": 1.277993209368744e-07, "loss": 0.1271, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.3181073073426843, "learning_rate": 1.214956261808542e-07, "loss": 0.1382, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.3926398533411024, "learning_rate": 1.1535087941609846e-07, "loss": 0.143, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.32939036873045346, "learning_rate": 1.0936512977583802e-07, "loss": 0.157, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.3514365658809961, "learning_rate": 1.0353842512196732e-07, "loss": 0.3344, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.3920045850389459, "learning_rate": 9.787081204466253e-08, "loss": 0.1968, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.4295484545821115, "learning_rate": 9.236233586200627e-08, "loss": 0.1258, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.3860124553849516, "learning_rate": 8.70130406196279e-08, "loss": 0.1337, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.3728090920940578, "learning_rate": 8.182296909035047e-08, "loss": 0.1184, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.34620050404447383, "learning_rate": 7.679216277384439e-08, "loss": 0.0972, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.34541515091961417, "learning_rate": 7.19206618963053e-08, "loss": 0.0978, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.35006800156055556, "learning_rate": 6.720850541012347e-08, "loss": 0.1218, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.4508810129532806, "learning_rate": 6.265573099357714e-08, "loss": 0.1341, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.3231985036170904, "learning_rate": 5.826237505053067e-08, "loss": 0.139, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.31543811187940635, "learning_rate": 5.4028472710137e-08, "loss": 0.1037, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.36372269096277077, "learning_rate": 4.9954057826571146e-08, "loss": 0.1114, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.365393085043154, "learning_rate": 4.6039162978743776e-08, "loss": 0.1326, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.30502700404172906, "learning_rate": 4.228381947004812e-08, "loss": 0.112, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.313017334938121, "learning_rate": 3.868805732811343e-08, "loss": 0.1222, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.3220461626077421, "learning_rate": 3.525190530455636e-08, "loss": 0.0977, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.3538238927375363, "learning_rate": 3.197539087475887e-08, "loss": 0.1505, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.3297212267926142, "learning_rate": 2.8858540237641786e-08, "loss": 0.1029, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.3990089805592355, "learning_rate": 2.5901378315458247e-08, "loss": 0.1003, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.34299341644434367, "learning_rate": 2.3103928753598347e-08, "loss": 0.1383, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.3553333546112733, "learning_rate": 2.0466213920393718e-08, "loss": 0.2184, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.39211064755436825, "learning_rate": 1.7988254906942115e-08, "loss": 0.1203, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.34986145691610937, "learning_rate": 1.5670071526936447e-08, "loss": 0.2435, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.37787482484558493, "learning_rate": 1.3511682316509344e-08, "loss": 0.1086, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.34402673741851764, "learning_rate": 1.1513104534086605e-08, "loss": 0.1061, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.4107103798074068, "learning_rate": 9.67435416023843e-09, "loss": 0.1988, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.3945226791656848, "learning_rate": 7.995445897566178e-09, "loss": 0.1096, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.35190817971623206, "learning_rate": 6.476393170578021e-09, "loss": 0.1274, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.34241624389820075, "learning_rate": 5.11720812557348e-09, "loss": 0.1443, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.38981428320553557, "learning_rate": 3.917901630563492e-09, "loss": 0.1176, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.3174893591144336, "learning_rate": 2.878483275170485e-09, "loss": 0.1226, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 1.081037842294615, "learning_rate": 1.998961370555108e-09, "loss": 0.1521, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.40756401128849706, "learning_rate": 1.2793429493518361e-09, "loss": 0.2515, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.35726289000447214, "learning_rate": 7.196337656112384e-10, "loss": 0.1218, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.35081618159747785, "learning_rate": 3.198382947511292e-10, "loss": 0.1086, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.32179175641963376, "learning_rate": 7.995973352770137e-11, "loss": 0.1341, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.41505875912379636, "learning_rate": 0.0, "loss": 0.13, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 8.321297243680276e+17, "train_loss": 0.3467648260928841, "train_runtime": 20539.6042, "train_samples_per_second": 7.692, "train_steps_per_second": 0.06 } ], "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": 8.321297243680276e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }