{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 6.454629186791858, "learning_rate": 3.2258064516129035e-07, "loss": 1.0364, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.348929911562485, "learning_rate": 6.451612903225807e-07, "loss": 1.015, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.511587645962333, "learning_rate": 9.67741935483871e-07, "loss": 1.0457, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.404980998610598, "learning_rate": 1.2903225806451614e-06, "loss": 1.027, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.02000756301601, "learning_rate": 1.6129032258064516e-06, "loss": 1.0352, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.7418007739288965, "learning_rate": 1.935483870967742e-06, "loss": 1.011, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.597385627572061, "learning_rate": 2.2580645161290324e-06, "loss": 0.9943, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.2238922531079615, "learning_rate": 2.580645161290323e-06, "loss": 0.9803, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.7104891954099557, "learning_rate": 2.903225806451613e-06, "loss": 0.9497, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.569713339195181, "learning_rate": 3.225806451612903e-06, "loss": 0.9531, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.420029377087213, "learning_rate": 3.548387096774194e-06, "loss": 0.9507, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.6916309482380645, "learning_rate": 3.870967741935484e-06, "loss": 0.9432, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.9698363683719182, "learning_rate": 4.193548387096774e-06, "loss": 0.9256, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.9563995805819197, "learning_rate": 4.516129032258065e-06, "loss": 0.9159, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.7195343293463288, "learning_rate": 4.838709677419355e-06, "loss": 0.907, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.781347599122578, "learning_rate": 5.161290322580646e-06, "loss": 0.8814, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.514606865559184, "learning_rate": 5.483870967741935e-06, "loss": 0.8516, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.096539373905348, "learning_rate": 5.806451612903226e-06, "loss": 0.8805, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.5830653827280485, "learning_rate": 6.129032258064517e-06, "loss": 0.849, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.2021711004383033, "learning_rate": 6.451612903225806e-06, "loss": 0.8259, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.0848767090993616, "learning_rate": 6.774193548387097e-06, "loss": 0.8194, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.2532770295582387, "learning_rate": 7.096774193548388e-06, "loss": 0.8, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.1908706609356445, "learning_rate": 7.4193548387096784e-06, "loss": 0.7994, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.9828073001681324, "learning_rate": 7.741935483870968e-06, "loss": 0.7839, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.9316586949392114, "learning_rate": 8.064516129032258e-06, "loss": 0.7761, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.9799951032977302, "learning_rate": 8.387096774193549e-06, "loss": 0.764, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.8681886228154788, "learning_rate": 8.70967741935484e-06, "loss": 0.7622, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8347831306578032, "learning_rate": 9.03225806451613e-06, "loss": 0.7692, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.8406233000393274, "learning_rate": 9.35483870967742e-06, "loss": 0.7527, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.776583919287051, "learning_rate": 9.67741935483871e-06, "loss": 0.731, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.7221252671703629, "learning_rate": 1e-05, "loss": 0.7481, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.6382283776485667, "learning_rate": 1.0322580645161291e-05, "loss": 0.7383, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7022079889668147, "learning_rate": 1.0645161290322582e-05, "loss": 0.7259, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.6538850815905938, "learning_rate": 1.096774193548387e-05, "loss": 0.7207, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.5984964877181338, "learning_rate": 1.1290322580645164e-05, "loss": 0.7287, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.5727002512004977, "learning_rate": 1.1612903225806453e-05, "loss": 0.7219, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.6010926886982104, "learning_rate": 1.1935483870967743e-05, "loss": 0.7084, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.5531723313827147, "learning_rate": 1.2258064516129034e-05, "loss": 0.7203, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5030495865011734, "learning_rate": 1.2580645161290324e-05, "loss": 0.693, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.615779950359734, "learning_rate": 1.2903225806451613e-05, "loss": 0.7051, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.5846564511194542, "learning_rate": 1.3225806451612903e-05, "loss": 0.6942, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5356370508044727, "learning_rate": 1.3548387096774194e-05, "loss": 0.6958, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.4995185112636095, "learning_rate": 1.3870967741935486e-05, "loss": 0.6967, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5844860822901673, "learning_rate": 1.4193548387096776e-05, "loss": 0.6906, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.5564993236876495, "learning_rate": 1.4516129032258066e-05, "loss": 0.6989, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.550980056319107, "learning_rate": 1.4838709677419357e-05, "loss": 0.6691, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.6243929910995719, "learning_rate": 1.5161290322580646e-05, "loss": 0.7048, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.530005141344507, "learning_rate": 1.5483870967741936e-05, "loss": 0.694, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5422031957688958, "learning_rate": 1.5806451612903226e-05, "loss": 0.6861, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.5208998937525914, "learning_rate": 1.6129032258064517e-05, "loss": 0.6712, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.43776253234668316, "learning_rate": 1.6451612903225807e-05, "loss": 0.6981, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.5509507733312085, "learning_rate": 1.6774193548387098e-05, "loss": 0.6819, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.5976762899602898, "learning_rate": 1.7096774193548388e-05, "loss": 0.6849, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5712689587455863, "learning_rate": 1.741935483870968e-05, "loss": 0.6856, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7053929042202296, "learning_rate": 1.774193548387097e-05, "loss": 0.6755, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.5506400371337905, "learning_rate": 1.806451612903226e-05, "loss": 0.6574, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.7057304456223636, "learning_rate": 1.838709677419355e-05, "loss": 0.6674, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6714980554877753, "learning_rate": 1.870967741935484e-05, "loss": 0.6704, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5430765310608069, "learning_rate": 1.903225806451613e-05, "loss": 0.6665, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.4967130607130981, "learning_rate": 1.935483870967742e-05, "loss": 0.6552, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.572300039926088, "learning_rate": 1.967741935483871e-05, "loss": 0.6633, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.5157420655521574, "learning_rate": 2e-05, "loss": 0.6668, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6754660273631629, "learning_rate": 2.0322580645161292e-05, "loss": 0.6713, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7378279518963821, "learning_rate": 2.0645161290322582e-05, "loss": 0.6665, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.5145747492560883, "learning_rate": 2.0967741935483873e-05, "loss": 0.6608, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.8643369417208817, "learning_rate": 2.1290322580645163e-05, "loss": 0.6653, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7801464885413467, "learning_rate": 2.161290322580645e-05, "loss": 0.6659, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.8141465459947343, "learning_rate": 2.193548387096774e-05, "loss": 0.6657, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 1.0140843095108396, "learning_rate": 2.225806451612903e-05, "loss": 0.6546, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.023783628538136, "learning_rate": 2.2580645161290328e-05, "loss": 0.6569, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.818724067530021, "learning_rate": 2.2903225806451615e-05, "loss": 0.6637, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.6751646070756792, "learning_rate": 2.3225806451612906e-05, "loss": 0.6582, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 1.06576705754055, "learning_rate": 2.3548387096774196e-05, "loss": 0.6649, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 1.0287484948149077, "learning_rate": 2.3870967741935486e-05, "loss": 0.6544, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.9810407492756646, "learning_rate": 2.4193548387096777e-05, "loss": 0.6638, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.848090280600364, "learning_rate": 2.4516129032258067e-05, "loss": 0.6429, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.1181396079929025, "learning_rate": 2.4838709677419358e-05, "loss": 0.6559, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7859370634611273, "learning_rate": 2.5161290322580648e-05, "loss": 0.6474, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8350224734451167, "learning_rate": 2.548387096774194e-05, "loss": 0.6633, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.1329057638505395, "learning_rate": 2.5806451612903226e-05, "loss": 0.6493, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.9670796152186174, "learning_rate": 2.6129032258064516e-05, "loss": 0.6497, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.6125942895750793, "learning_rate": 2.6451612903225806e-05, "loss": 0.638, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8591925256210078, "learning_rate": 2.6774193548387097e-05, "loss": 0.6448, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 2.1714089882066405, "learning_rate": 2.7096774193548387e-05, "loss": 0.6535, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.5088943448159298, "learning_rate": 2.7419354838709678e-05, "loss": 0.6529, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.7965171445215788, "learning_rate": 2.774193548387097e-05, "loss": 0.6356, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 1.8081591630676637, "learning_rate": 2.8064516129032262e-05, "loss": 0.6572, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.1748435272486255, "learning_rate": 2.8387096774193552e-05, "loss": 0.6495, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.5378344359767235, "learning_rate": 2.8709677419354843e-05, "loss": 0.6483, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.8698618520649707, "learning_rate": 2.9032258064516133e-05, "loss": 0.6296, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.2666268457935537, "learning_rate": 2.9354838709677423e-05, "loss": 0.6444, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.4486447924603945, "learning_rate": 2.9677419354838714e-05, "loss": 0.6401, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.8678987508532452, "learning_rate": 3.0000000000000004e-05, "loss": 0.6347, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.5856035270982918, "learning_rate": 3.032258064516129e-05, "loss": 0.6439, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.2781223529385894, "learning_rate": 3.0645161290322585e-05, "loss": 0.6402, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.8892489377215697, "learning_rate": 3.096774193548387e-05, "loss": 0.6404, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.2888788531826807, "learning_rate": 3.1290322580645166e-05, "loss": 0.6417, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.9807784971603803, "learning_rate": 3.161290322580645e-05, "loss": 0.6505, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.3056290026157584, "learning_rate": 3.193548387096774e-05, "loss": 0.6489, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.5496102459091172, "learning_rate": 3.2258064516129034e-05, "loss": 0.6398, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.8330151346492709, "learning_rate": 3.258064516129033e-05, "loss": 0.6387, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.173506882709502, "learning_rate": 3.2903225806451614e-05, "loss": 0.6344, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 1.4462613987614608, "learning_rate": 3.322580645161291e-05, "loss": 0.6486, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.0416737653719321, "learning_rate": 3.3548387096774195e-05, "loss": 0.6366, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.3067459364510108, "learning_rate": 3.387096774193549e-05, "loss": 0.6459, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.7134104790410971, "learning_rate": 3.4193548387096776e-05, "loss": 0.635, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 1.5658589691150544, "learning_rate": 3.451612903225807e-05, "loss": 0.6461, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.0723094789479684, "learning_rate": 3.483870967741936e-05, "loss": 0.6483, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.3210909517278826, "learning_rate": 3.516129032258065e-05, "loss": 0.6418, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.8672896511014808, "learning_rate": 3.548387096774194e-05, "loss": 0.6322, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.2351105702401983, "learning_rate": 3.5806451612903225e-05, "loss": 0.6309, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.9126798713860013, "learning_rate": 3.612903225806452e-05, "loss": 0.6377, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.196400196142593, "learning_rate": 3.6451612903225805e-05, "loss": 0.6264, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.149766193461487, "learning_rate": 3.67741935483871e-05, "loss": 0.6262, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.0423595675590986, "learning_rate": 3.7096774193548386e-05, "loss": 0.6329, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.7023749847906714, "learning_rate": 3.741935483870968e-05, "loss": 0.6158, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.0886044943210405, "learning_rate": 3.7741935483870974e-05, "loss": 0.6376, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.3555571501386638, "learning_rate": 3.806451612903226e-05, "loss": 0.6276, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.0175815382987283, "learning_rate": 3.8387096774193555e-05, "loss": 0.6377, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.8220588317164313, "learning_rate": 3.870967741935484e-05, "loss": 0.6316, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.6929749533939056, "learning_rate": 3.9032258064516135e-05, "loss": 0.6348, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6882287640792562, "learning_rate": 3.935483870967742e-05, "loss": 0.6289, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 1.1441050194635385, "learning_rate": 3.9677419354838716e-05, "loss": 0.6274, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.6369573529544643, "learning_rate": 4e-05, "loss": 0.6264, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.6745108889266774, "learning_rate": 3.9999920040266474e-05, "loss": 0.6268, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.6499772257292702, "learning_rate": 3.999968016170525e-05, "loss": 0.6178, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.6966688761068797, "learning_rate": 3.9999280366234394e-05, "loss": 0.6383, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.2496436047184654, "learning_rate": 3.999872065705065e-05, "loss": 0.6345, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 1.1530759889419575, "learning_rate": 3.999800103862945e-05, "loss": 0.6276, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.8967793660036569, "learning_rate": 3.9997121516724834e-05, "loss": 0.6271, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.3384773499886027, "learning_rate": 3.999608209836944e-05, "loss": 0.6367, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.6076417566614122, "learning_rate": 3.999488279187443e-05, "loss": 0.6331, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.9088062640174772, "learning_rate": 3.9993523606829425e-05, "loss": 0.6242, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 1.0220257969717577, "learning_rate": 3.9992004554102435e-05, "loss": 0.6202, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 1.0375003741660398, "learning_rate": 3.999032564583976e-05, "loss": 0.6242, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.3341758090650857, "learning_rate": 3.998848689546591e-05, "loss": 0.6157, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.8350599369828863, "learning_rate": 3.9986488317683496e-05, "loss": 0.6166, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 1.249833553351377, "learning_rate": 3.9984329928473067e-05, "loss": 0.6231, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.8532061067018816, "learning_rate": 3.998201174509306e-05, "loss": 0.6217, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6873121242656569, "learning_rate": 3.997953378607961e-05, "loss": 0.6198, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.9786803099539466, "learning_rate": 3.9976896071246403e-05, "loss": 0.6224, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 1.1841240230059003, "learning_rate": 3.997409862168454e-05, "loss": 0.6054, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.7563255742378037, "learning_rate": 3.997114145976237e-05, "loss": 0.6101, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5803050017041924, "learning_rate": 3.9968024609125245e-05, "loss": 0.6287, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7245081895353633, "learning_rate": 3.996474809469545e-05, "loss": 0.6138, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.8383101128782525, "learning_rate": 3.996131194267189e-05, "loss": 0.624, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.9487519510335728, "learning_rate": 3.995771618052995e-05, "loss": 0.6273, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.9230083237774757, "learning_rate": 3.9953960837021256e-05, "loss": 0.6318, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 1.0733977596689108, "learning_rate": 3.995004594217343e-05, "loss": 0.6154, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.8737501600628529, "learning_rate": 3.994597152728987e-05, "loss": 0.632, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.4852013300091187, "learning_rate": 3.994173762494947e-05, "loss": 0.6561, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6646207768235821, "learning_rate": 3.9937344269006424e-05, "loss": 0.6058, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7381404368992677, "learning_rate": 3.993279149458988e-05, "loss": 0.6337, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.735464053664127, "learning_rate": 3.9928079338103695e-05, "loss": 0.5884, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.7105511600768026, "learning_rate": 3.992320783722616e-05, "loss": 0.6075, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.637328785655897, "learning_rate": 3.991817703090965e-05, "loss": 0.6179, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.5870296709168888, "learning_rate": 3.991298695938038e-05, "loss": 0.6276, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.878454427771711, "learning_rate": 3.9907637664138e-05, "loss": 0.6268, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7294862048875514, "learning_rate": 3.990212918795534e-05, "loss": 0.6263, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.577322418214937, "learning_rate": 3.9896461574878036e-05, "loss": 0.604, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.5404395519832271, "learning_rate": 3.989063487022416e-05, "loss": 0.5919, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.4672404223101862, "learning_rate": 3.9884649120583903e-05, "loss": 0.6229, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5296521328733864, "learning_rate": 3.987850437381915e-05, "loss": 0.6091, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6648205556030498, "learning_rate": 3.987220067906313e-05, "loss": 0.6016, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.6352578564219911, "learning_rate": 3.986573808672002e-05, "loss": 0.6177, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.7580045299964224, "learning_rate": 3.9859116648464534e-05, "loss": 0.6028, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.7208473868788224, "learning_rate": 3.985233641724152e-05, "loss": 0.6146, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7012688240004572, "learning_rate": 3.984539744726554e-05, "loss": 0.6079, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6903013552059729, "learning_rate": 3.983829979402038e-05, "loss": 0.6242, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.6720352085096118, "learning_rate": 3.983104351425871e-05, "loss": 0.6111, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6484042567165713, "learning_rate": 3.982362866600154e-05, "loss": 0.6127, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6107187469249149, "learning_rate": 3.9816055308537806e-05, "loss": 0.6025, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.7302799721048508, "learning_rate": 3.980832350242388e-05, "loss": 0.5925, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.8309864502434303, "learning_rate": 3.980043330948306e-05, "loss": 0.5949, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.49503490457738797, "learning_rate": 3.9792384792805124e-05, "loss": 0.6322, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.8026581283487559, "learning_rate": 3.978417801674579e-05, "loss": 0.6106, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.8335810608619852, "learning_rate": 3.9775813046926244e-05, "loss": 0.604, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5503812443162348, "learning_rate": 3.976728995023254e-05, "loss": 0.6196, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.9020617019202695, "learning_rate": 3.975860879481514e-05, "loss": 0.6265, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.7834050340330483, "learning_rate": 3.974976965008833e-05, "loss": 0.5968, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.518191265531961, "learning_rate": 3.9740772586729674e-05, "loss": 0.6005, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.7037640223829862, "learning_rate": 3.973161767667946e-05, "loss": 0.5975, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6003034361009376, "learning_rate": 3.972230499314009e-05, "loss": 0.6065, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.6523377310046271, "learning_rate": 3.9712834610575545e-05, "loss": 0.6131, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.6932897128441482, "learning_rate": 3.9703206604710746e-05, "loss": 0.613, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.6299624643790173, "learning_rate": 3.969342105253098e-05, "loss": 0.6294, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.5272067591083119, "learning_rate": 3.9683478032281246e-05, "loss": 0.6011, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5815341074648878, "learning_rate": 3.967337762346568e-05, "loss": 0.6164, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.5478219320965821, "learning_rate": 3.9663119906846885e-05, "loss": 0.6383, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5645886800251851, "learning_rate": 3.965270496444528e-05, "loss": 0.6135, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.5229664066859122, "learning_rate": 3.9642132879538465e-05, "loss": 0.6098, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5833893695991594, "learning_rate": 3.9631403736660566e-05, "loss": 0.5976, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.48731174411020434, "learning_rate": 3.962051762160151e-05, "loss": 0.6081, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.619186035207902, "learning_rate": 3.960947462140638e-05, "loss": 0.5985, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.48080757271790003, "learning_rate": 3.959827482437472e-05, "loss": 0.6037, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.41492024093356883, "learning_rate": 3.958691832005981e-05, "loss": 0.6048, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.43270515887733785, "learning_rate": 3.9575405199267944e-05, "loss": 0.623, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.4568512779666211, "learning_rate": 3.956373555405774e-05, "loss": 0.5855, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.42783156463393723, "learning_rate": 3.955190947773937e-05, "loss": 0.6096, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.5099354426960635, "learning_rate": 3.9539927064873824e-05, "loss": 0.6204, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6029503337333774, "learning_rate": 3.952778841127214e-05, "loss": 0.6203, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.44700952545884837, "learning_rate": 3.95154936139947e-05, "loss": 0.603, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.54439952663728, "learning_rate": 3.950304277135034e-05, "loss": 0.6126, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.6788201803834117, "learning_rate": 3.94904359828957e-05, "loss": 0.5943, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5487651581315309, "learning_rate": 3.94776733494343e-05, "loss": 0.6025, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.5300232866252578, "learning_rate": 3.9464754973015826e-05, "loss": 0.6181, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5373025805620428, "learning_rate": 3.9451680956935275e-05, "loss": 0.6004, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5504007905505307, "learning_rate": 3.943845140573213e-05, "loss": 0.6085, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.6365485013495239, "learning_rate": 3.942506642518952e-05, "loss": 0.5988, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.720533415647076, "learning_rate": 3.9411526122333396e-05, "loss": 0.6035, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.8074791930197424, "learning_rate": 3.939783060543167e-05, "loss": 0.5798, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.6532558537734797, "learning_rate": 3.938397998399333e-05, "loss": 0.5991, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6362406364795098, "learning_rate": 3.936997436876756e-05, "loss": 0.6096, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6973629271402882, "learning_rate": 3.935581387174289e-05, "loss": 0.5929, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.6008653022087085, "learning_rate": 3.9341498606146295e-05, "loss": 0.5859, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.5060279502022104, "learning_rate": 3.932702868644224e-05, "loss": 0.5866, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.6381993228421665, "learning_rate": 3.931240422833181e-05, "loss": 0.6044, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.4716501703830675, "learning_rate": 3.9297625348751806e-05, "loss": 0.6075, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5126788335233408, "learning_rate": 3.9282692165873744e-05, "loss": 0.5865, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.622091387179317, "learning_rate": 3.9267604799102945e-05, "loss": 0.6031, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.48826689997093436, "learning_rate": 3.9252363369077615e-05, "loss": 0.5901, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5098360215361856, "learning_rate": 3.9236967997667796e-05, "loss": 0.5891, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.559481479152524, "learning_rate": 3.9221418807974496e-05, "loss": 0.5964, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.40937912073084715, "learning_rate": 3.92057159243286e-05, "loss": 0.6068, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.4923096334557133, "learning_rate": 3.9189859472289956e-05, "loss": 0.6062, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.48559398397505804, "learning_rate": 3.9173849578646324e-05, "loss": 0.5831, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.4805346425552166, "learning_rate": 3.9157686371412395e-05, "loss": 0.5782, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5444474167572212, "learning_rate": 3.914136997982874e-05, "loss": 0.5912, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5204257223537283, "learning_rate": 3.912490053436079e-05, "loss": 0.6011, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5042975761676668, "learning_rate": 3.9108278166697805e-05, "loss": 0.5968, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.7441923566313776, "learning_rate": 3.909150300975178e-05, "loss": 0.5884, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.5941497390455603, "learning_rate": 3.907457519765642e-05, "loss": 0.595, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5719490152833091, "learning_rate": 3.905749486576607e-05, "loss": 0.5834, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6157371353421649, "learning_rate": 3.90402621506546e-05, "loss": 0.5829, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4488769174659309, "learning_rate": 3.902287719011435e-05, "loss": 0.5814, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.510062404923654, "learning_rate": 3.900534012315499e-05, "loss": 0.6031, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.6979335387793582, "learning_rate": 3.8987651090002454e-05, "loss": 0.5911, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7229804568067651, "learning_rate": 3.896981023209777e-05, "loss": 0.6048, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.423326566980032, "learning_rate": 3.8951817692095966e-05, "loss": 0.5854, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4837849324311861, "learning_rate": 3.893367361386491e-05, "loss": 0.5904, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.6116813060846271, "learning_rate": 3.891537814248417e-05, "loss": 0.5844, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.6858892302020265, "learning_rate": 3.889693142424384e-05, "loss": 0.5939, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.778608728242629, "learning_rate": 3.8878333606643405e-05, "loss": 0.592, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6140764763482109, "learning_rate": 3.885958483839049e-05, "loss": 0.5792, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.49981199568709017, "learning_rate": 3.8840685269399786e-05, "loss": 0.5886, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.571105857895552, "learning_rate": 3.882163505079171e-05, "loss": 0.6126, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5786130150020229, "learning_rate": 3.880243433489132e-05, "loss": 0.5877, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.6144486048809948, "learning_rate": 3.878308327522702e-05, "loss": 0.5468, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.5133737173881273, "learning_rate": 3.876358202652936e-05, "loss": 0.5557, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5143268699969344, "learning_rate": 3.8743930744729835e-05, "loss": 0.5494, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.43827475263634813, "learning_rate": 3.8724129586959535e-05, "loss": 0.5273, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.6216218116616302, "learning_rate": 3.870417871154801e-05, "loss": 0.5523, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6202984178939096, "learning_rate": 3.868407827802192e-05, "loss": 0.5226, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5888143091747203, "learning_rate": 3.8663828447103804e-05, "loss": 0.5577, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6189655017290197, "learning_rate": 3.8643429380710765e-05, "loss": 0.5625, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6294025247691825, "learning_rate": 3.862288124195319e-05, "loss": 0.5517, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.50909312847529, "learning_rate": 3.8602184195133464e-05, "loss": 0.5419, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.4173536449269869, "learning_rate": 3.8581338405744604e-05, "loss": 0.5434, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.624891057017873, "learning_rate": 3.8560344040468996e-05, "loss": 0.5385, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5058665216661851, "learning_rate": 3.853920126717703e-05, "loss": 0.5441, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6073713144206768, "learning_rate": 3.851791025492574e-05, "loss": 0.545, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.6428546622916612, "learning_rate": 3.8496471173957515e-05, "loss": 0.5484, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.5511493654162685, "learning_rate": 3.847488419569866e-05, "loss": 0.5411, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.506502964033628, "learning_rate": 3.8453149492758077e-05, "loss": 0.5522, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.5162337515899496, "learning_rate": 3.8431267238925886e-05, "loss": 0.5345, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.6377172653410363, "learning_rate": 3.840923760917199e-05, "loss": 0.546, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5233325264462111, "learning_rate": 3.838706077964473e-05, "loss": 0.55, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.5691348318113678, "learning_rate": 3.836473692766944e-05, "loss": 0.5536, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5796590636346608, "learning_rate": 3.834226623174705e-05, "loss": 0.5197, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.47644049746782907, "learning_rate": 3.831964887155264e-05, "loss": 0.5486, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.5425474558880766, "learning_rate": 3.829688502793403e-05, "loss": 0.5426, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.46137838423853555, "learning_rate": 3.827397488291029e-05, "loss": 0.5444, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.42735787398002556, "learning_rate": 3.8250918619670343e-05, "loss": 0.5421, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.46344970169936633, "learning_rate": 3.822771642257145e-05, "loss": 0.5416, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.4684956370387279, "learning_rate": 3.820436847713776e-05, "loss": 0.5356, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.516505640745502, "learning_rate": 3.8180874970058826e-05, "loss": 0.5323, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5489827399516746, "learning_rate": 3.8157236089188103e-05, "loss": 0.5417, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.7234836506720064, "learning_rate": 3.813345202354145e-05, "loss": 0.557, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.4285123689351533, "learning_rate": 3.810952296329563e-05, "loss": 0.5355, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.620757970624783, "learning_rate": 3.808544909978676e-05, "loss": 0.5407, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.6543370872825824, "learning_rate": 3.806123062550882e-05, "loss": 0.5394, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.5695529884733014, "learning_rate": 3.803686773411208e-05, "loss": 0.5477, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.4294057483393896, "learning_rate": 3.801236062040158e-05, "loss": 0.5533, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.4114853582763215, "learning_rate": 3.798770948033553e-05, "loss": 0.5343, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4514916834292469, "learning_rate": 3.796291451102381e-05, "loss": 0.547, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5368679265531985, "learning_rate": 3.793797591072631e-05, "loss": 0.5369, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.46132344879543397, "learning_rate": 3.791289387885144e-05, "loss": 0.537, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.38296139549567454, "learning_rate": 3.788766861595443e-05, "loss": 0.5516, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.40150620052420727, "learning_rate": 3.7862300323735835e-05, "loss": 0.5472, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.38743967508754096, "learning_rate": 3.783678920503983e-05, "loss": 0.5558, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.3982773384794694, "learning_rate": 3.781113546385265e-05, "loss": 0.5491, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.4619392742633793, "learning_rate": 3.7785339305300916e-05, "loss": 0.5461, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.3877079378786166, "learning_rate": 3.7759400935650025e-05, "loss": 0.5466, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.44035583860582544, "learning_rate": 3.77333205623025e-05, "loss": 0.5681, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.43702473559087046, "learning_rate": 3.7707098393796295e-05, "loss": 0.542, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.4804032606688227, "learning_rate": 3.7680734639803185e-05, "loss": 0.5411, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5218907330155189, "learning_rate": 3.765422951112704e-05, "loss": 0.5362, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.44962279615171197, "learning_rate": 3.762758321970216e-05, "loss": 0.5369, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.4333963023801126, "learning_rate": 3.7600795978591584e-05, "loss": 0.5555, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.447104739873957, "learning_rate": 3.757386800198538e-05, "loss": 0.5488, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.44966118931679144, "learning_rate": 3.7546799505198925e-05, "loss": 0.5416, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.39552349433260553, "learning_rate": 3.7519590704671197e-05, "loss": 0.5359, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.43502656763097897, "learning_rate": 3.749224181796305e-05, "loss": 0.5445, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.46356648603008355, "learning_rate": 3.746475306375545e-05, "loss": 0.5494, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5437586383477803, "learning_rate": 3.743712466184774e-05, "loss": 0.5552, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.4852496164724253, "learning_rate": 3.7409356833155885e-05, "loss": 0.5417, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4941540053359941, "learning_rate": 3.73814497997107e-05, "loss": 0.539, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.35360952463928036, "learning_rate": 3.7353403784656095e-05, "loss": 0.5484, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5627018521930922, "learning_rate": 3.732521901224724e-05, "loss": 0.5367, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.5731916687416718, "learning_rate": 3.7296895707848844e-05, "loss": 0.5428, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.5377839785120968, "learning_rate": 3.7268434097933275e-05, "loss": 0.5536, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.6099096564650992, "learning_rate": 3.723983441007882e-05, "loss": 0.5531, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.49352316126649587, "learning_rate": 3.721109687296781e-05, "loss": 0.5452, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.4802932728462994, "learning_rate": 3.718222171638484e-05, "loss": 0.5261, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5680824483508268, "learning_rate": 3.715320917121488e-05, "loss": 0.552, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.43390297209503037, "learning_rate": 3.712405946944149e-05, "loss": 0.5458, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.4748610739189323, "learning_rate": 3.709477284414488e-05, "loss": 0.5399, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.5548039258050362, "learning_rate": 3.7065349529500136e-05, "loss": 0.5663, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.4880021407491278, "learning_rate": 3.7035789760775305e-05, "loss": 0.5322, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.4438941269089342, "learning_rate": 3.70060937743295e-05, "loss": 0.5356, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.45342724632766696, "learning_rate": 3.6976261807611045e-05, "loss": 0.5365, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.556429553428382, "learning_rate": 3.694629409915555e-05, "loss": 0.556, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.49778147776874415, "learning_rate": 3.691619088858401e-05, "loss": 0.5535, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.43299696573524005, "learning_rate": 3.68859524166009e-05, "loss": 0.5443, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.7141225287712949, "learning_rate": 3.6855578924992226e-05, "loss": 0.5473, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.47890461625505615, "learning_rate": 3.6825070656623626e-05, "loss": 0.5441, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.4523038616066351, "learning_rate": 3.67944278554384e-05, "loss": 0.5427, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.5572161051053438, "learning_rate": 3.676365076645557e-05, "loss": 0.5435, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4295195575936701, "learning_rate": 3.673273963576791e-05, "loss": 0.527, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.5796391658299067, "learning_rate": 3.670169471054001e-05, "loss": 0.5356, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.44395392071103207, "learning_rate": 3.6670516239006254e-05, "loss": 0.5391, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.44016668344185733, "learning_rate": 3.663920447046888e-05, "loss": 0.536, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.4137064112148, "learning_rate": 3.6607759655295954e-05, "loss": 0.5406, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.40491437954485276, "learning_rate": 3.657618204491937e-05, "loss": 0.5426, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.43046850852616303, "learning_rate": 3.6544471891832875e-05, "loss": 0.5424, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4027397477916213, "learning_rate": 3.6512629449589983e-05, "loss": 0.5468, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.3731981575643307, "learning_rate": 3.6480654972802045e-05, "loss": 0.5502, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.4206138147861173, "learning_rate": 3.644854871713611e-05, "loss": 0.5497, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.46540426104584254, "learning_rate": 3.6416310939312924e-05, "loss": 0.5375, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.5384227237323168, "learning_rate": 3.638394189710493e-05, "loss": 0.5527, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.3670401874947742, "learning_rate": 3.635144184933412e-05, "loss": 0.5352, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.404953369099665, "learning_rate": 3.6318811055869994e-05, "loss": 0.547, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.4489678219663262, "learning_rate": 3.628604977762752e-05, "loss": 0.5377, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.37462664741627444, "learning_rate": 3.6253158276565004e-05, "loss": 0.5513, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.34515700533531657, "learning_rate": 3.6220136815682016e-05, "loss": 0.554, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.37713260765330403, "learning_rate": 3.618698565901727e-05, "loss": 0.5482, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.4180672579531956, "learning_rate": 3.615370507164654e-05, "loss": 0.5642, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.36282721993416206, "learning_rate": 3.61202953196805e-05, "loss": 0.5536, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.48321422790601626, "learning_rate": 3.6086756670262654e-05, "loss": 0.5477, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4116246475345317, "learning_rate": 3.6053089391567135e-05, "loss": 0.5405, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.44827182279814776, "learning_rate": 3.601929375279662e-05, "loss": 0.5322, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.42006819997629374, "learning_rate": 3.598537002418012e-05, "loss": 0.5447, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.44475690394002304, "learning_rate": 3.5951318476970885e-05, "loss": 0.5463, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.38196550331260437, "learning_rate": 3.591713938344416e-05, "loss": 0.5348, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.44511170526946126, "learning_rate": 3.588283301689507e-05, "loss": 0.5354, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.43522539495318985, "learning_rate": 3.5848399651636424e-05, "loss": 0.54, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.44237875780016567, "learning_rate": 3.5813839562996473e-05, "loss": 0.5513, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.36889505629061253, "learning_rate": 3.5779153027316775e-05, "loss": 0.5273, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.44357065786028876, "learning_rate": 3.574434032194994e-05, "loss": 0.5446, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.41683278966378734, "learning_rate": 3.5709401725257436e-05, "loss": 0.5398, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.37145529909451797, "learning_rate": 3.5674337516607346e-05, "loss": 0.5427, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.43290227383561425, "learning_rate": 3.563914797637216e-05, "loss": 0.5346, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5088251198528175, "learning_rate": 3.560383338592649e-05, "loss": 0.5427, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.43576655159507244, "learning_rate": 3.556839402764487e-05, "loss": 0.5398, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.373055258161353, "learning_rate": 3.553283018489946e-05, "loss": 0.5334, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5546871659107556, "learning_rate": 3.54971421420578e-05, "loss": 0.5441, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.558489106464408, "learning_rate": 3.5461330184480524e-05, "loss": 0.5292, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.395248824557118, "learning_rate": 3.54253945985191e-05, "loss": 0.5332, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.3970627433036672, "learning_rate": 3.5389335671513524e-05, "loss": 0.5499, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.4553387071061058, "learning_rate": 3.5353153691789986e-05, "loss": 0.5537, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.47933404453636047, "learning_rate": 3.531684894865866e-05, "loss": 0.544, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5575890989336951, "learning_rate": 3.528042173241128e-05, "loss": 0.5469, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4139817866948151, "learning_rate": 3.524387233431892e-05, "loss": 0.5468, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.46520975653440516, "learning_rate": 3.520720104662958e-05, "loss": 0.5428, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.5427920948017111, "learning_rate": 3.5170408162565904e-05, "loss": 0.5329, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.41189417936957395, "learning_rate": 3.513349397632281e-05, "loss": 0.5398, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.3730624256305478, "learning_rate": 3.5096458783065145e-05, "loss": 0.5483, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5074746695724964, "learning_rate": 3.505930287892533e-05, "loss": 0.5383, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.36474968865655155, "learning_rate": 3.502202656100099e-05, "loss": 0.5419, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.4008853790175026, "learning_rate": 3.498463012735256e-05, "loss": 0.532, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.3948051470515932, "learning_rate": 3.494711387700094e-05, "loss": 0.5467, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.3547970895545093, "learning_rate": 3.490947810992505e-05, "loss": 0.5493, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.40208790365537456, "learning_rate": 3.48717231270595e-05, "loss": 0.5457, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.3953276558507443, "learning_rate": 3.483384923029211e-05, "loss": 0.5316, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.33285211961397715, "learning_rate": 3.479585672246156e-05, "loss": 0.5417, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.3672912521234895, "learning_rate": 3.4757745907354924e-05, "loss": 0.5236, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.36192229176669494, "learning_rate": 3.471951708970527e-05, "loss": 0.5357, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4900270660122892, "learning_rate": 3.468117057518921e-05, "loss": 0.5755, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.32864712616535174, "learning_rate": 3.4642706670424426e-05, "loss": 0.545, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.41905193749754216, "learning_rate": 3.460412568296731e-05, "loss": 0.5262, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.370714068666634, "learning_rate": 3.456542792131039e-05, "loss": 0.5284, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.3595506006953928, "learning_rate": 3.4526613694879936e-05, "loss": 0.5324, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.35072164423109004, "learning_rate": 3.448768331403348e-05, "loss": 0.5301, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.4170660577642743, "learning_rate": 3.44486370900573e-05, "loss": 0.5382, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.3132068160704882, "learning_rate": 3.440947533516396e-05, "loss": 0.5328, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.33354066044181063, "learning_rate": 3.4370198362489816e-05, "loss": 0.5346, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.38768027934849497, "learning_rate": 3.43308064860925e-05, "loss": 0.5522, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.297381846664838, "learning_rate": 3.4291300020948393e-05, "loss": 0.5327, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.3511734875797968, "learning_rate": 3.425167928295015e-05, "loss": 0.5275, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.44266525676204804, "learning_rate": 3.421194458890411e-05, "loss": 0.5386, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.5003353640985834, "learning_rate": 3.4172096256527865e-05, "loss": 0.5219, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.36435803827069285, "learning_rate": 3.4132134604447595e-05, "loss": 0.5309, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.4198047374847974, "learning_rate": 3.409205995219561e-05, "loss": 0.5298, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.40461849052324433, "learning_rate": 3.4051872620207765e-05, "loss": 0.5549, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.49051644841446707, "learning_rate": 3.40115729298209e-05, "loss": 0.548, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.41654774884035645, "learning_rate": 3.397116120327025e-05, "loss": 0.5338, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.479713724386616, "learning_rate": 3.3930637763686916e-05, "loss": 0.5377, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.5008778008992135, "learning_rate": 3.389000293509524e-05, "loss": 0.5446, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5416977016695504, "learning_rate": 3.3849257042410225e-05, "loss": 0.5486, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5553733831121617, "learning_rate": 3.380840041143494e-05, "loss": 0.5357, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.4176657806308371, "learning_rate": 3.376743336885792e-05, "loss": 0.5426, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4755637778764729, "learning_rate": 3.372635624225055e-05, "loss": 0.5134, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.5097595847607752, "learning_rate": 3.3685169360064445e-05, "loss": 0.5392, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.425591629717122, "learning_rate": 3.3643873051628804e-05, "loss": 0.5463, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4324481736478501, "learning_rate": 3.3602467647147814e-05, "loss": 0.5396, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.45236146387766746, "learning_rate": 3.356095347769799e-05, "loss": 0.5305, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.36633192269710324, "learning_rate": 3.351933087522552e-05, "loss": 0.5297, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.417620418275489, "learning_rate": 3.3477600172543626e-05, "loss": 0.5473, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.42303165228377, "learning_rate": 3.3435761703329894e-05, "loss": 0.5464, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.37484225748067074, "learning_rate": 3.3393815802123606e-05, "loss": 0.5495, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.45211686010171553, "learning_rate": 3.335176280432308e-05, "loss": 0.534, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.4052835904860234, "learning_rate": 3.330960304618295e-05, "loss": 0.5451, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4223995559318812, "learning_rate": 3.326733686481153e-05, "loss": 0.535, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.3193718253172359, "learning_rate": 3.3224964598168084e-05, "loss": 0.5316, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.39033418390795505, "learning_rate": 3.318248658506012e-05, "loss": 0.5368, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.4118791249528574, "learning_rate": 3.313990316514069e-05, "loss": 0.5494, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.32787812118884985, "learning_rate": 3.309721467890571e-05, "loss": 0.5327, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.49204541503730737, "learning_rate": 3.305442146769115e-05, "loss": 0.549, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.4987787720700162, "learning_rate": 3.30115238736704e-05, "loss": 0.5308, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.38518281314393193, "learning_rate": 3.296852223985148e-05, "loss": 0.5344, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4702758527141573, "learning_rate": 3.2925416910074315e-05, "loss": 0.5357, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.427924176885308, "learning_rate": 3.288220822900796e-05, "loss": 0.5298, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.4464779437696121, "learning_rate": 3.283889654214788e-05, "loss": 0.537, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.4776386131660379, "learning_rate": 3.279548219581317e-05, "loss": 0.5281, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.3978030054715547, "learning_rate": 3.275196553714379e-05, "loss": 0.5393, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.375465814672488, "learning_rate": 3.270834691409778e-05, "loss": 0.5259, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.43104406874246787, "learning_rate": 3.266462667544849e-05, "loss": 0.5487, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.3769365950223414, "learning_rate": 3.262080517078178e-05, "loss": 0.536, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.4431568632609829, "learning_rate": 3.257688275049323e-05, "loss": 0.5342, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.516562897348207, "learning_rate": 3.253285976578535e-05, "loss": 0.5233, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.36956722121491087, "learning_rate": 3.2488736568664756e-05, "loss": 0.5305, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.5610428268082097, "learning_rate": 3.244451351193935e-05, "loss": 0.5272, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.5016211508874299, "learning_rate": 3.240019094921551e-05, "loss": 0.5385, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.36846350905228914, "learning_rate": 3.235576923489527e-05, "loss": 0.5227, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.5353328364556458, "learning_rate": 3.2311248724173476e-05, "loss": 0.5308, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.386163302884682, "learning_rate": 3.226662977303494e-05, "loss": 0.5427, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4321106289459004, "learning_rate": 3.2221912738251626e-05, "loss": 0.5442, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.32912764961690927, "learning_rate": 3.2177097977379736e-05, "loss": 0.5352, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.4026333677532207, "learning_rate": 3.21321858487569e-05, "loss": 0.5164, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.39692517362093627, "learning_rate": 3.208717671149931e-05, "loss": 0.5272, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4055586074223475, "learning_rate": 3.204207092549882e-05, "loss": 0.5313, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.33471158677096285, "learning_rate": 3.19968688514201e-05, "loss": 0.5332, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.41131525714913625, "learning_rate": 3.195157085069774e-05, "loss": 0.5346, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.41102783538019627, "learning_rate": 3.190617728553332e-05, "loss": 0.5328, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.34909601481570274, "learning_rate": 3.1860688518892606e-05, "loss": 0.5372, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4092462391547872, "learning_rate": 3.181510491450254e-05, "loss": 0.5348, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.38013820185010233, "learning_rate": 3.176942683684842e-05, "loss": 0.5263, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.33788420947792036, "learning_rate": 3.1723654651170934e-05, "loss": 0.5417, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.5360185998487905, "learning_rate": 3.167778872346327e-05, "loss": 0.5441, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.496918011223086, "learning_rate": 3.163182942046815e-05, "loss": 0.5279, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.3813806521395845, "learning_rate": 3.158577710967494e-05, "loss": 0.5368, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.45022827217032946, "learning_rate": 3.153963215931669e-05, "loss": 0.5335, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.5022231036693814, "learning_rate": 3.14933949383672e-05, "loss": 0.5326, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.4104079567789001, "learning_rate": 3.144706581653805e-05, "loss": 0.5376, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.38713309256282247, "learning_rate": 3.140064516427566e-05, "loss": 0.522, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.536944230346823, "learning_rate": 3.135413335275833e-05, "loss": 0.5304, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.3897411464974278, "learning_rate": 3.130753075389327e-05, "loss": 0.5389, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4109489103402847, "learning_rate": 3.1260837740313625e-05, "loss": 0.5396, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.47342066264422, "learning_rate": 3.121405468537547e-05, "loss": 0.5183, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.42010153910894005, "learning_rate": 3.116718196315488e-05, "loss": 0.5225, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.332390769193056, "learning_rate": 3.1120219948444894e-05, "loss": 0.5393, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.41984870223985143, "learning_rate": 3.107316901675252e-05, "loss": 0.5308, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3693854313499889, "learning_rate": 3.1026029544295745e-05, "loss": 0.5418, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.3867146395028478, "learning_rate": 3.097880190800057e-05, "loss": 0.5349, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3709126554317959, "learning_rate": 3.093148648549788e-05, "loss": 0.5375, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.35394252299540974, "learning_rate": 3.088408365512055e-05, "loss": 0.5446, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.34602568303720493, "learning_rate": 3.083659379590034e-05, "loss": 0.5375, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.392250080679733, "learning_rate": 3.0789017287564913e-05, "loss": 0.5489, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.3588077789259106, "learning_rate": 3.074135451053475e-05, "loss": 0.5339, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3799538810477738, "learning_rate": 3.069360584592015e-05, "loss": 0.5386, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.41895589545177353, "learning_rate": 3.064577167551816e-05, "loss": 0.5286, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.32343692807854735, "learning_rate": 3.059785238180953e-05, "loss": 0.5253, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.2926569796520354, "learning_rate": 3.054984834795566e-05, "loss": 0.5145, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.38353759378642377, "learning_rate": 3.0501759957795537e-05, "loss": 0.5377, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.43783311802682545, "learning_rate": 3.0453587595842627e-05, "loss": 0.5183, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4389691108116913, "learning_rate": 3.0405331647281856e-05, "loss": 0.5493, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.3444074280725247, "learning_rate": 3.0356992497966508e-05, "loss": 0.5279, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.39408168074873257, "learning_rate": 3.0308570534415137e-05, "loss": 0.5325, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.40896640144718205, "learning_rate": 3.0260066143808467e-05, "loss": 0.5305, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.3228845502046695, "learning_rate": 3.021147971398632e-05, "loss": 0.5305, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.3585618459348534, "learning_rate": 3.0162811633444478e-05, "loss": 0.5268, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.411516224420792, "learning_rate": 3.0114062291331635e-05, "loss": 0.5439, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.32206557859406976, "learning_rate": 3.0065232077446217e-05, "loss": 0.5202, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.4084832861429771, "learning_rate": 3.001632138223332e-05, "loss": 0.5286, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.49729428940814496, "learning_rate": 2.9967330596781565e-05, "loss": 0.4706, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.3933543900584153, "learning_rate": 2.9918260112819952e-05, "loss": 0.4689, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.6165720105744869, "learning_rate": 2.9869110322714778e-05, "loss": 0.465, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.4372586056758791, "learning_rate": 2.9819881619466447e-05, "loss": 0.4768, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.4803879084915227, "learning_rate": 2.9770574396706364e-05, "loss": 0.4756, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.4215049747508641, "learning_rate": 2.972118904869376e-05, "loss": 0.4568, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.46124308562124866, "learning_rate": 2.9671725970312563e-05, "loss": 0.4631, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5255022491541039, "learning_rate": 2.9622185557068238e-05, "loss": 0.4751, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.4306678023047234, "learning_rate": 2.95725682050846e-05, "loss": 0.4692, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.4689916840474156, "learning_rate": 2.9522874311100684e-05, "loss": 0.4777, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.40029866505313166, "learning_rate": 2.9473104272467526e-05, "loss": 0.4547, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4260407903258244, "learning_rate": 2.942325848714505e-05, "loss": 0.4769, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.4849873579163101, "learning_rate": 2.9373337353698804e-05, "loss": 0.4668, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.41428616520209455, "learning_rate": 2.932334127129686e-05, "loss": 0.4531, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.3676965511573113, "learning_rate": 2.9273270639706547e-05, "loss": 0.4611, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.46561899324964146, "learning_rate": 2.922312585929131e-05, "loss": 0.4684, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.3957808039012048, "learning_rate": 2.9172907331007478e-05, "loss": 0.4724, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.37816623358970936, "learning_rate": 2.9122615456401053e-05, "loss": 0.4584, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.37594927833456765, "learning_rate": 2.9072250637604535e-05, "loss": 0.4572, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.37813454494423127, "learning_rate": 2.9021813277333667e-05, "loss": 0.4618, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.4001900203280545, "learning_rate": 2.8971303778884244e-05, "loss": 0.4729, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.38252929144269276, "learning_rate": 2.8920722546128863e-05, "loss": 0.4663, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.40511054510757, "learning_rate": 2.887006998351372e-05, "loss": 0.4641, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4539770909904277, "learning_rate": 2.881934649605535e-05, "loss": 0.4617, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.34874733999476526, "learning_rate": 2.8768552489337408e-05, "loss": 0.4693, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.3763983690317452, "learning_rate": 2.8717688369507425e-05, "loss": 0.4709, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.406571846767514, "learning_rate": 2.8666754543273535e-05, "loss": 0.4716, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.37282575024639064, "learning_rate": 2.8615751417901273e-05, "loss": 0.4591, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.39875890136153064, "learning_rate": 2.856467940121025e-05, "loss": 0.4598, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.3856321738692906, "learning_rate": 2.8513538901570964e-05, "loss": 0.4769, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3339891415047729, "learning_rate": 2.846233032790149e-05, "loss": 0.466, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.318866245028191, "learning_rate": 2.84110540896642e-05, "loss": 0.4713, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.35726816175803705, "learning_rate": 2.8359710596862555e-05, "loss": 0.4631, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.29773799289015696, "learning_rate": 2.8308300260037734e-05, "loss": 0.4584, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3423670769442394, "learning_rate": 2.8256823490265424e-05, "loss": 0.4615, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.35546793312725655, "learning_rate": 2.8205280699152515e-05, "loss": 0.469, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.3937886156113551, "learning_rate": 2.8153672298833777e-05, "loss": 0.4652, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.36152302393268265, "learning_rate": 2.8101998701968615e-05, "loss": 0.457, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.3319616016263229, "learning_rate": 2.805026032173773e-05, "loss": 0.4618, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3623774468647322, "learning_rate": 2.7998457571839832e-05, "loss": 0.4728, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.32603810364058794, "learning_rate": 2.7946590866488322e-05, "loss": 0.4669, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.2885664503267988, "learning_rate": 2.7894660620408e-05, "loss": 0.4643, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.3738785098415727, "learning_rate": 2.784266724883173e-05, "loss": 0.4722, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.32472249980923945, "learning_rate": 2.7790611167497128e-05, "loss": 0.4723, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.31942447481000413, "learning_rate": 2.7738492792643224e-05, "loss": 0.4807, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.33443673453448003, "learning_rate": 2.768631254100716e-05, "loss": 0.4701, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.342595283844587, "learning_rate": 2.7634070829820836e-05, "loss": 0.4725, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.34003673257543526, "learning_rate": 2.7581768076807592e-05, "loss": 0.4648, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.35741760096576, "learning_rate": 2.7529404700178832e-05, "loss": 0.4559, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3803924639680696, "learning_rate": 2.7476981118630735e-05, "loss": 0.4823, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.35980571101597064, "learning_rate": 2.742449775134085e-05, "loss": 0.469, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.4226874153899285, "learning_rate": 2.7371955017964788e-05, "loss": 0.4605, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.35489592857898494, "learning_rate": 2.7319353338632845e-05, "loss": 0.4692, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.29813613454761806, "learning_rate": 2.7266693133946645e-05, "loss": 0.4697, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.4223221972135529, "learning_rate": 2.7213974824975785e-05, "loss": 0.4545, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.33075048043116173, "learning_rate": 2.7161198833254464e-05, "loss": 0.4732, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.38179397195404635, "learning_rate": 2.7108365580778095e-05, "loss": 0.4727, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.4257483261988078, "learning_rate": 2.705547548999996e-05, "loss": 0.469, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.37681991590589725, "learning_rate": 2.7002528983827817e-05, "loss": 0.4754, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3234664787120049, "learning_rate": 2.6949526485620517e-05, "loss": 0.4709, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.4108026704700753, "learning_rate": 2.6896468419184623e-05, "loss": 0.463, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.3080444568195415, "learning_rate": 2.6843355208771024e-05, "loss": 0.4739, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.34660747967479294, "learning_rate": 2.6790187279071536e-05, "loss": 0.4663, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.3388064209664222, "learning_rate": 2.67369650552155e-05, "loss": 0.4722, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.33664827423250965, "learning_rate": 2.6683688962766407e-05, "loss": 0.4676, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.3347306440537486, "learning_rate": 2.6630359427718468e-05, "loss": 0.4823, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3734022756975888, "learning_rate": 2.6576976876493225e-05, "loss": 0.4729, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.317147278406606, "learning_rate": 2.652354173593614e-05, "loss": 0.4728, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.40791964262730185, "learning_rate": 2.647005443331317e-05, "loss": 0.4634, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3469848467753811, "learning_rate": 2.6416515396307354e-05, "loss": 0.4572, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3828688079231718, "learning_rate": 2.636292505301542e-05, "loss": 0.4897, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.42871068584265204, "learning_rate": 2.630928383194431e-05, "loss": 0.4678, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3298334007472156, "learning_rate": 2.625559216200781e-05, "loss": 0.4713, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.40105456772031084, "learning_rate": 2.620185047252308e-05, "loss": 0.4708, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.35075130874009697, "learning_rate": 2.614805919320723e-05, "loss": 0.4607, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3173832365175177, "learning_rate": 2.6094218754173895e-05, "loss": 0.4489, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3439910034679127, "learning_rate": 2.60403295859298e-05, "loss": 0.4682, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3685079095121721, "learning_rate": 2.5986392119371297e-05, "loss": 0.4755, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.30963387147642946, "learning_rate": 2.5932406785780928e-05, "loss": 0.4772, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3862933887208964, "learning_rate": 2.5878374016823987e-05, "loss": 0.4734, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.35171498529634154, "learning_rate": 2.5824294244545045e-05, "loss": 0.4664, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.350463985647879, "learning_rate": 2.577016790136453e-05, "loss": 0.4794, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3603427994585022, "learning_rate": 2.5715995420075225e-05, "loss": 0.473, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.3563889812794939, "learning_rate": 2.5661777233838864e-05, "loss": 0.4689, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.32850893313934443, "learning_rate": 2.5607513776182616e-05, "loss": 0.4646, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.378860987267963, "learning_rate": 2.5553205480995633e-05, "loss": 0.466, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.39665810800443035, "learning_rate": 2.5498852782525604e-05, "loss": 0.4657, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.364754621037648, "learning_rate": 2.5444456115375252e-05, "loss": 0.4674, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3795821668977424, "learning_rate": 2.539001591449889e-05, "loss": 0.4874, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.36093953732431383, "learning_rate": 2.53355326151989e-05, "loss": 0.4739, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.38388562472239046, "learning_rate": 2.5281006653122288e-05, "loss": 0.4751, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3123962448693178, "learning_rate": 2.5226438464257217e-05, "loss": 0.4705, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.33898582032220104, "learning_rate": 2.5171828484929447e-05, "loss": 0.4607, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3725115685123594, "learning_rate": 2.5117177151798934e-05, "loss": 0.4784, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.32578938380036143, "learning_rate": 2.506248490185627e-05, "loss": 0.4763, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.4370357652606262, "learning_rate": 2.500775217241923e-05, "loss": 0.4655, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4030398194743012, "learning_rate": 2.4952979401129266e-05, "loss": 0.4702, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3474170982064054, "learning_rate": 2.4898167025948e-05, "loss": 0.4756, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.4470258658062096, "learning_rate": 2.4843315485153703e-05, "loss": 0.4787, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.292569835464219, "learning_rate": 2.4788425217337856e-05, "loss": 0.4905, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.41628411376754676, "learning_rate": 2.4733496661401572e-05, "loss": 0.4643, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.33236542806789704, "learning_rate": 2.4678530256552114e-05, "loss": 0.4855, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.39369106991227404, "learning_rate": 2.46235264422994e-05, "loss": 0.4697, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.42181477489816593, "learning_rate": 2.4568485658452452e-05, "loss": 0.4695, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.33235793632226074, "learning_rate": 2.451340834511592e-05, "loss": 0.4804, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.3646654160343424, "learning_rate": 2.4458294942686528e-05, "loss": 0.4584, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.36962042704345033, "learning_rate": 2.440314589184958e-05, "loss": 0.4724, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.3953101192204653, "learning_rate": 2.434796163357541e-05, "loss": 0.4891, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3649925979287721, "learning_rate": 2.429274260911588e-05, "loss": 0.4656, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.40496539110997076, "learning_rate": 2.423748926000084e-05, "loss": 0.4736, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.38549728934817146, "learning_rate": 2.418220202803459e-05, "loss": 0.4793, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.4324692387540003, "learning_rate": 2.412688135529237e-05, "loss": 0.458, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3318802026595132, "learning_rate": 2.4071527684116807e-05, "loss": 0.4673, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.3509540803234142, "learning_rate": 2.4016141457114372e-05, "loss": 0.4858, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.32773271781741303, "learning_rate": 2.396072311715187e-05, "loss": 0.4777, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.33977327894958387, "learning_rate": 2.3905273107352863e-05, "loss": 0.4794, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.32303516750369915, "learning_rate": 2.3849791871094157e-05, "loss": 0.4669, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.34278587333595845, "learning_rate": 2.379427985200223e-05, "loss": 0.4785, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3516813403871031, "learning_rate": 2.373873749394972e-05, "loss": 0.4719, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.330663376002286, "learning_rate": 2.3683165241051836e-05, "loss": 0.4807, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.3016035292514703, "learning_rate": 2.3627563537662823e-05, "loss": 0.4614, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.3502251859177773, "learning_rate": 2.3571932828372433e-05, "loss": 0.4628, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3017947951699534, "learning_rate": 2.351627355800233e-05, "loss": 0.4672, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.31999009784747967, "learning_rate": 2.346058617160256e-05, "loss": 0.4613, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.314537266564649, "learning_rate": 2.3404871114447976e-05, "loss": 0.4689, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3035522772523322, "learning_rate": 2.334912883203469e-05, "loss": 0.4766, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.33889454292599935, "learning_rate": 2.3293359770076505e-05, "loss": 0.4706, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.2908126490635507, "learning_rate": 2.323756437450136e-05, "loss": 0.4734, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.3406821387932103, "learning_rate": 2.3181743091447754e-05, "loss": 0.4721, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.32633681897602007, "learning_rate": 2.3125896367261164e-05, "loss": 0.4681, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.32576120832218985, "learning_rate": 2.307002464849052e-05, "loss": 0.4706, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.33131559255885484, "learning_rate": 2.30141283818846e-05, "loss": 0.479, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3194887352840494, "learning_rate": 2.2958208014388462e-05, "loss": 0.4662, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.33249306779857246, "learning_rate": 2.2902263993139857e-05, "loss": 0.4684, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.29992288918004106, "learning_rate": 2.2846296765465708e-05, "loss": 0.4632, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.309794084508798, "learning_rate": 2.2790306778878465e-05, "loss": 0.4775, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.30608915871751213, "learning_rate": 2.273429448107257e-05, "loss": 0.4713, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3150700471065593, "learning_rate": 2.2678260319920868e-05, "loss": 0.4683, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.2776987221578912, "learning_rate": 2.262220474347102e-05, "loss": 0.4708, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.2967252666540903, "learning_rate": 2.2566128199941918e-05, "loss": 0.4664, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.30236380850857725, "learning_rate": 2.2510031137720104e-05, "loss": 0.4641, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.291300840953449, "learning_rate": 2.2453914005356206e-05, "loss": 0.4728, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.28641873550437447, "learning_rate": 2.2397777251561302e-05, "loss": 0.4713, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.31112892348185733, "learning_rate": 2.2341621325203393e-05, "loss": 0.4695, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.29392262009908365, "learning_rate": 2.2285446675303764e-05, "loss": 0.4683, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.32290938679149583, "learning_rate": 2.2229253751033423e-05, "loss": 0.4697, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.27844290563618374, "learning_rate": 2.2173043001709492e-05, "loss": 0.4644, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.31008207906279234, "learning_rate": 2.2116814876791627e-05, "loss": 0.465, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.2686919502726255, "learning_rate": 2.2060569825878413e-05, "loss": 0.4618, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.26868853727820463, "learning_rate": 2.2004308298703777e-05, "loss": 0.4754, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.31283017085744225, "learning_rate": 2.1948030745133396e-05, "loss": 0.4695, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.32890752479322444, "learning_rate": 2.1891737615161083e-05, "loss": 0.4671, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3112022821730684, "learning_rate": 2.1835429358905218e-05, "loss": 0.4627, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.29419219591028334, "learning_rate": 2.17791064266051e-05, "loss": 0.4693, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.2969910216110802, "learning_rate": 2.172276926861741e-05, "loss": 0.4778, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.3153457833145326, "learning_rate": 2.166641833541255e-05, "loss": 0.4674, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.31138525056834615, "learning_rate": 2.161005407757109e-05, "loss": 0.4738, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.337746950781595, "learning_rate": 2.155367694578013e-05, "loss": 0.4734, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.28833017484625745, "learning_rate": 2.1497287390829712e-05, "loss": 0.4607, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.31490406612177, "learning_rate": 2.1440885863609208e-05, "loss": 0.4567, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.29344318316163537, "learning_rate": 2.1384472815103737e-05, "loss": 0.4859, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.29556195435604454, "learning_rate": 2.1328048696390534e-05, "loss": 0.4552, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.29292756563518324, "learning_rate": 2.1271613958635342e-05, "loss": 0.472, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.31706259497820694, "learning_rate": 2.1215169053088825e-05, "loss": 0.469, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.27876564100151907, "learning_rate": 2.1158714431082937e-05, "loss": 0.4729, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3259833848130179, "learning_rate": 2.110225054402733e-05, "loss": 0.4621, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.2873873917349364, "learning_rate": 2.1045777843405747e-05, "loss": 0.4733, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.2992619032262211, "learning_rate": 2.09892967807724e-05, "loss": 0.4731, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.28473602865776465, "learning_rate": 2.093280780774835e-05, "loss": 0.4668, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.3146069626225512, "learning_rate": 2.087631137601793e-05, "loss": 0.4678, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.26959283599884265, "learning_rate": 2.0819807937325104e-05, "loss": 0.4706, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.31030622292646426, "learning_rate": 2.0763297943469847e-05, "loss": 0.4694, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.26371361482364725, "learning_rate": 2.070678184630458e-05, "loss": 0.4678, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.31421832493565716, "learning_rate": 2.06502600977305e-05, "loss": 0.463, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.2756376288293687, "learning_rate": 2.0593733149694008e-05, "loss": 0.4787, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.30082403817814785, "learning_rate": 2.0537201454183074e-05, "loss": 0.4518, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.26136085511515433, "learning_rate": 2.0480665463223626e-05, "loss": 0.4578, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.2874301203063132, "learning_rate": 2.042412562887594e-05, "loss": 0.4731, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.2549342233310989, "learning_rate": 2.0367582403231033e-05, "loss": 0.467, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.30751374194639486, "learning_rate": 2.0311036238407023e-05, "loss": 0.4688, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.26471320607091925, "learning_rate": 2.0254487586545534e-05, "loss": 0.4577, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.31241952843393106, "learning_rate": 2.0197936899808088e-05, "loss": 0.4691, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.2653526086453034, "learning_rate": 2.0141384630372466e-05, "loss": 0.476, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.33846434902555256, "learning_rate": 2.0084831230429106e-05, "loss": 0.4663, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.28494674988078955, "learning_rate": 2.0028277152177492e-05, "loss": 0.4745, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3202382376243071, "learning_rate": 1.9971722847822518e-05, "loss": 0.4599, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.2996183712669844, "learning_rate": 1.99151687695709e-05, "loss": 0.4754, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.328665012530105, "learning_rate": 1.9858615369627537e-05, "loss": 0.471, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.2683124994594458, "learning_rate": 1.9802063100191916e-05, "loss": 0.46, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.32240428350171885, "learning_rate": 1.974551241345447e-05, "loss": 0.4712, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.2598230285979459, "learning_rate": 1.9688963761592984e-05, "loss": 0.4648, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3382379210485587, "learning_rate": 1.963241759676897e-05, "loss": 0.4527, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.25895926114689866, "learning_rate": 1.9575874371124066e-05, "loss": 0.4795, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.2978931120235081, "learning_rate": 1.951933453677638e-05, "loss": 0.4852, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.253263150398883, "learning_rate": 1.9462798545816932e-05, "loss": 0.4724, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.27436008342250945, "learning_rate": 1.9406266850305996e-05, "loss": 0.4611, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.26076280051473727, "learning_rate": 1.9349739902269503e-05, "loss": 0.4694, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.27334123366061236, "learning_rate": 1.9293218153695425e-05, "loss": 0.4652, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.28549549352364945, "learning_rate": 1.9236702056530153e-05, "loss": 0.4728, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.30854473734172233, "learning_rate": 1.9180192062674907e-05, "loss": 0.4755, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.293941186098962, "learning_rate": 1.9123688623982076e-05, "loss": 0.4667, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.2521794201930878, "learning_rate": 1.906719219225165e-05, "loss": 0.4756, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.25380496893823756, "learning_rate": 1.9010703219227603e-05, "loss": 0.4759, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.2891794045367021, "learning_rate": 1.8954222156594256e-05, "loss": 0.4766, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.243979552088285, "learning_rate": 1.8897749455972673e-05, "loss": 0.481, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.28776336097327687, "learning_rate": 1.884128556891707e-05, "loss": 0.4698, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.2734379887361834, "learning_rate": 1.878483094691119e-05, "loss": 0.47, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.27747994769140855, "learning_rate": 1.8728386041364664e-05, "loss": 0.4731, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.2675868959888516, "learning_rate": 1.867195130360947e-05, "loss": 0.4706, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.2978457753487443, "learning_rate": 1.8615527184896263e-05, "loss": 0.457, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.2673840908288652, "learning_rate": 1.8559114136390795e-05, "loss": 0.4531, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.27299479227218165, "learning_rate": 1.8502712609170298e-05, "loss": 0.4706, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.2792922288925231, "learning_rate": 1.8446323054219876e-05, "loss": 0.489, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.2527072208465339, "learning_rate": 1.838994592242891e-05, "loss": 0.4725, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.27963759092862633, "learning_rate": 1.8333581664587453e-05, "loss": 0.4621, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.25060462170832415, "learning_rate": 1.8277230731382593e-05, "loss": 0.4788, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.28233766656599535, "learning_rate": 1.82208935733949e-05, "loss": 0.4653, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.26873943823410906, "learning_rate": 1.8164570641094793e-05, "loss": 0.4689, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.2976116713514768, "learning_rate": 1.810826238483892e-05, "loss": 0.463, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.26595092523779695, "learning_rate": 1.8051969254866608e-05, "loss": 0.4645, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.32692753616009385, "learning_rate": 1.7995691701296226e-05, "loss": 0.4667, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.27441018828657787, "learning_rate": 1.7939430174121593e-05, "loss": 0.4657, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.318101085970673, "learning_rate": 1.788318512320838e-05, "loss": 0.4733, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.26971001382103404, "learning_rate": 1.782695699829051e-05, "loss": 0.4679, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.28330510317942587, "learning_rate": 1.7770746248966587e-05, "loss": 0.455, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.24415529832393262, "learning_rate": 1.7714553324696243e-05, "loss": 0.4623, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.34713878053191116, "learning_rate": 1.7658378674796614e-05, "loss": 0.4609, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.2882252581796749, "learning_rate": 1.76022227484387e-05, "loss": 0.4775, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.29092444963014874, "learning_rate": 1.7546085994643807e-05, "loss": 0.4662, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.2591721672562836, "learning_rate": 1.7489968862279902e-05, "loss": 0.466, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.30784217098037864, "learning_rate": 1.743387180005809e-05, "loss": 0.4654, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.2521104929582833, "learning_rate": 1.737779525652899e-05, "loss": 0.475, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.28759867876395134, "learning_rate": 1.732173968007914e-05, "loss": 0.4664, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.26496733496407965, "learning_rate": 1.7265705518927437e-05, "loss": 0.4802, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.26954248922681906, "learning_rate": 1.7209693221121542e-05, "loss": 0.4571, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.28984238962502623, "learning_rate": 1.7153703234534302e-05, "loss": 0.4668, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.26363234695968374, "learning_rate": 1.709773600686015e-05, "loss": 0.4681, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.27187787693422705, "learning_rate": 1.7041791985611548e-05, "loss": 0.4708, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.26809628753387454, "learning_rate": 1.69858716181154e-05, "loss": 0.4774, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.25349447912454937, "learning_rate": 1.692997535150948e-05, "loss": 0.4768, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.25003592751185566, "learning_rate": 1.687410363273884e-05, "loss": 0.4681, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.26152836595712986, "learning_rate": 1.6818256908552257e-05, "loss": 0.4646, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.26807865026153316, "learning_rate": 1.6762435625498646e-05, "loss": 0.472, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.4494623278627416, "learning_rate": 1.67066402299235e-05, "loss": 0.4917, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.27168073067488163, "learning_rate": 1.6650871167965313e-05, "loss": 0.4753, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.29612331939182385, "learning_rate": 1.6595128885552028e-05, "loss": 0.4609, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.2911621233675143, "learning_rate": 1.653941382839745e-05, "loss": 0.4517, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.45051668116089694, "learning_rate": 1.6483726441997673e-05, "loss": 0.3939, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.5119008181975387, "learning_rate": 1.642806717162757e-05, "loss": 0.3991, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.43587032289782573, "learning_rate": 1.637243646233718e-05, "loss": 0.3998, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.578643527112461, "learning_rate": 1.6316834758948174e-05, "loss": 0.3935, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.39866075665135653, "learning_rate": 1.6261262506050282e-05, "loss": 0.3973, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4361280200867201, "learning_rate": 1.620572014799777e-05, "loss": 0.412, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.3963421524971451, "learning_rate": 1.6150208128905857e-05, "loss": 0.4154, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.39636865010737027, "learning_rate": 1.6094726892647147e-05, "loss": 0.4094, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.3989282409516547, "learning_rate": 1.6039276882848135e-05, "loss": 0.4073, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.3713496512031781, "learning_rate": 1.5983858542885635e-05, "loss": 0.408, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3987987205893527, "learning_rate": 1.5928472315883203e-05, "loss": 0.3955, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.384003395363728, "learning_rate": 1.5873118644707633e-05, "loss": 0.4044, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.4256251484822573, "learning_rate": 1.5817797971965413e-05, "loss": 0.4077, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.39044713582002705, "learning_rate": 1.576251073999917e-05, "loss": 0.4096, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.32518115935853364, "learning_rate": 1.5707257390884126e-05, "loss": 0.4007, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.36456296411518446, "learning_rate": 1.5652038366424595e-05, "loss": 0.4021, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.33560697270280315, "learning_rate": 1.5596854108150424e-05, "loss": 0.4129, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.36414476689384767, "learning_rate": 1.5541705057313476e-05, "loss": 0.3995, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.2840366419209586, "learning_rate": 1.5486591654884086e-05, "loss": 0.4047, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.37253935499291674, "learning_rate": 1.543151434154755e-05, "loss": 0.3934, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.2878064511260992, "learning_rate": 1.5376473557700615e-05, "loss": 0.4062, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.32492640710500276, "learning_rate": 1.5321469743447893e-05, "loss": 0.3998, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.31832263188199356, "learning_rate": 1.5266503338598434e-05, "loss": 0.4076, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.30571775485587754, "learning_rate": 1.5211574782662149e-05, "loss": 0.4109, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3058574011550118, "learning_rate": 1.5156684514846307e-05, "loss": 0.4133, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.30429488762428564, "learning_rate": 1.5101832974052012e-05, "loss": 0.3991, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.2852252532559348, "learning_rate": 1.5047020598870737e-05, "loss": 0.4105, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2795584582395678, "learning_rate": 1.4992247827580778e-05, "loss": 0.3902, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.29226676759270204, "learning_rate": 1.493751509814374e-05, "loss": 0.3957, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.26966754614976735, "learning_rate": 1.4882822848201073e-05, "loss": 0.4019, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.24943349841296522, "learning_rate": 1.4828171515070553e-05, "loss": 0.4237, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2509475625515578, "learning_rate": 1.4773561535742793e-05, "loss": 0.3956, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.24740669686597333, "learning_rate": 1.4718993346877715e-05, "loss": 0.402, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.24896654071560803, "learning_rate": 1.466446738480111e-05, "loss": 0.3984, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.26294300604218585, "learning_rate": 1.460998408550112e-05, "loss": 0.4033, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.2614789942633653, "learning_rate": 1.4555543884624751e-05, "loss": 0.4056, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.2637232985087694, "learning_rate": 1.4501147217474402e-05, "loss": 0.399, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.2637902387647034, "learning_rate": 1.444679451900437e-05, "loss": 0.3946, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.3021801630298765, "learning_rate": 1.4392486223817397e-05, "loss": 0.4052, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.26231478709821676, "learning_rate": 1.4338222766161143e-05, "loss": 0.4093, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2917229526305116, "learning_rate": 1.4284004579924777e-05, "loss": 0.4089, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.27240367082912864, "learning_rate": 1.4229832098635479e-05, "loss": 0.4092, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.2791770403432464, "learning_rate": 1.4175705755454963e-05, "loss": 0.4054, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.27865102655481633, "learning_rate": 1.412162598317602e-05, "loss": 0.3915, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.2656160664481301, "learning_rate": 1.406759321421907e-05, "loss": 0.3913, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2662514491859914, "learning_rate": 1.401360788062871e-05, "loss": 0.4067, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.27452306041320323, "learning_rate": 1.3959670414070204e-05, "loss": 0.3893, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.27140531174964994, "learning_rate": 1.3905781245826108e-05, "loss": 0.4045, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.275295414120685, "learning_rate": 1.3851940806792778e-05, "loss": 0.4064, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.2660164798269231, "learning_rate": 1.379814952747693e-05, "loss": 0.4098, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2594121330368269, "learning_rate": 1.3744407837992193e-05, "loss": 0.3943, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.26217134714871726, "learning_rate": 1.3690716168055692e-05, "loss": 0.408, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.28649321838731023, "learning_rate": 1.363707494698459e-05, "loss": 0.4014, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.2496321425256566, "learning_rate": 1.358348460369265e-05, "loss": 0.41, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.30559865240594797, "learning_rate": 1.352994556668684e-05, "loss": 0.3993, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.22855624396156324, "learning_rate": 1.3476458264063865e-05, "loss": 0.4198, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.3124974743392106, "learning_rate": 1.342302312350678e-05, "loss": 0.4133, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.2620304120889731, "learning_rate": 1.3369640572281537e-05, "loss": 0.403, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.25320231202761473, "learning_rate": 1.3316311037233596e-05, "loss": 0.3875, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.3406597958877322, "learning_rate": 1.326303494478451e-05, "loss": 0.414, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.25577845692291035, "learning_rate": 1.3209812720928472e-05, "loss": 0.4056, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.3742164269811586, "learning_rate": 1.315664479122898e-05, "loss": 0.3987, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.28093808062658204, "learning_rate": 1.3103531580815378e-05, "loss": 0.4031, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.31561231397115297, "learning_rate": 1.3050473514379488e-05, "loss": 0.4012, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.31071632340325556, "learning_rate": 1.2997471016172188e-05, "loss": 0.3956, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.246478931127308, "learning_rate": 1.2944524510000042e-05, "loss": 0.4047, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2820802560983432, "learning_rate": 1.2891634419221908e-05, "loss": 0.4017, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.2425583737001934, "learning_rate": 1.2838801166745545e-05, "loss": 0.4025, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.26862657430894865, "learning_rate": 1.2786025175024216e-05, "loss": 0.4096, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.27686444333185073, "learning_rate": 1.2733306866053357e-05, "loss": 0.4063, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.24284754136765324, "learning_rate": 1.2680646661367163e-05, "loss": 0.4004, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.26436694147312867, "learning_rate": 1.2628044982035219e-05, "loss": 0.4128, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.22972243364599268, "learning_rate": 1.2575502248659155e-05, "loss": 0.3944, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.24356114606800258, "learning_rate": 1.2523018881369269e-05, "loss": 0.4142, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.23827276279562185, "learning_rate": 1.2470595299821176e-05, "loss": 0.4056, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2611033337966165, "learning_rate": 1.2418231923192416e-05, "loss": 0.3966, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.24581953138495907, "learning_rate": 1.2365929170179165e-05, "loss": 0.3964, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.24703591698258623, "learning_rate": 1.2313687458992848e-05, "loss": 0.3882, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.2685999037858868, "learning_rate": 1.2261507207356785e-05, "loss": 0.3946, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.23736877744419418, "learning_rate": 1.220938883250288e-05, "loss": 0.4227, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2665205372788101, "learning_rate": 1.215733275116827e-05, "loss": 0.4151, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.24043322014719917, "learning_rate": 1.2105339379592005e-05, "loss": 0.4096, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.23684069098512092, "learning_rate": 1.2053409133511681e-05, "loss": 0.391, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.22382984112698964, "learning_rate": 1.2001542428160173e-05, "loss": 0.4075, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2395238969896557, "learning_rate": 1.1949739678262278e-05, "loss": 0.4099, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.2425529667656442, "learning_rate": 1.189800129803139e-05, "loss": 0.4126, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.2283063547055991, "learning_rate": 1.1846327701166228e-05, "loss": 0.4213, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.24143446001353322, "learning_rate": 1.1794719300847493e-05, "loss": 0.4084, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2482215512504206, "learning_rate": 1.1743176509734582e-05, "loss": 0.424, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.25210087621725885, "learning_rate": 1.1691699739962275e-05, "loss": 0.4131, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.25259666611179155, "learning_rate": 1.1640289403137456e-05, "loss": 0.4124, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.25055341832817324, "learning_rate": 1.1588945910335802e-05, "loss": 0.3967, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.2562939648659664, "learning_rate": 1.1537669672098517e-05, "loss": 0.4108, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.23127245303612837, "learning_rate": 1.1486461098429036e-05, "loss": 0.4177, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.26229485401953484, "learning_rate": 1.1435320598789747e-05, "loss": 0.3956, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.24815307782142715, "learning_rate": 1.1384248582098736e-05, "loss": 0.3986, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.2444576325154206, "learning_rate": 1.1333245456726467e-05, "loss": 0.4042, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.26660370191503513, "learning_rate": 1.128231163049258e-05, "loss": 0.3979, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.24051271819938336, "learning_rate": 1.123144751066259e-05, "loss": 0.4197, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2266792520369076, "learning_rate": 1.1180653503944657e-05, "loss": 0.4008, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.27284400223933347, "learning_rate": 1.1129930016486287e-05, "loss": 0.3974, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.22586277791317588, "learning_rate": 1.107927745387114e-05, "loss": 0.4028, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.24553352954203841, "learning_rate": 1.1028696221115766e-05, "loss": 0.4093, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2726758583545989, "learning_rate": 1.0978186722666341e-05, "loss": 0.3932, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.2497846430232222, "learning_rate": 1.0927749362395475e-05, "loss": 0.4102, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.2513548013136348, "learning_rate": 1.0877384543598954e-05, "loss": 0.4102, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.247710124137138, "learning_rate": 1.0827092668992529e-05, "loss": 0.4068, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2741743987990659, "learning_rate": 1.077687414070869e-05, "loss": 0.3906, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.25763316634578504, "learning_rate": 1.0726729360293451e-05, "loss": 0.3913, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.25078988981414874, "learning_rate": 1.0676658728703147e-05, "loss": 0.3937, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.2584436552423362, "learning_rate": 1.0626662646301198e-05, "loss": 0.3946, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2535940921828613, "learning_rate": 1.0576741512854958e-05, "loss": 0.4026, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2624168450059492, "learning_rate": 1.052689572753247e-05, "loss": 0.4355, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2476947708041442, "learning_rate": 1.0477125688899328e-05, "loss": 0.4016, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.23691479504634438, "learning_rate": 1.0427431794915406e-05, "loss": 0.4072, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.24858337515167153, "learning_rate": 1.0377814442931769e-05, "loss": 0.4065, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2384194995288174, "learning_rate": 1.0328274029687439e-05, "loss": 0.4147, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.24091915134373593, "learning_rate": 1.0278810951306253e-05, "loss": 0.4148, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.25900915166870103, "learning_rate": 1.0229425603293647e-05, "loss": 0.4015, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.23889131348571255, "learning_rate": 1.0180118380533558e-05, "loss": 0.4174, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.23508201399481363, "learning_rate": 1.0130889677285225e-05, "loss": 0.4013, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.23026407025901344, "learning_rate": 1.008173988718005e-05, "loss": 0.4087, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.23359160976476953, "learning_rate": 1.0032669403218439e-05, "loss": 0.4249, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.23200295938058124, "learning_rate": 9.983678617766677e-06, "loss": 0.4043, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2501847419847874, "learning_rate": 9.934767922553788e-06, "loss": 0.404, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.262729845860975, "learning_rate": 9.885937708668371e-06, "loss": 0.4018, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.2513845573566241, "learning_rate": 9.837188366555524e-06, "loss": 0.4149, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.24829275368337267, "learning_rate": 9.788520286013691e-06, "loss": 0.3912, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2545925537835169, "learning_rate": 9.739933856191537e-06, "loss": 0.4061, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2412110583210739, "learning_rate": 9.691429465584866e-06, "loss": 0.4185, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.24243801973667703, "learning_rate": 9.643007502033492e-06, "loss": 0.413, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.2400540218102311, "learning_rate": 9.594668352718152e-06, "loss": 0.3871, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.2496526682907507, "learning_rate": 9.546412404157383e-06, "loss": 0.3944, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.23799734517607338, "learning_rate": 9.498240042204471e-06, "loss": 0.4104, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.25203130697844733, "learning_rate": 9.450151652044339e-06, "loss": 0.3932, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.24089512760163034, "learning_rate": 9.402147618190472e-06, "loss": 0.4068, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.23776296424284793, "learning_rate": 9.354228324481841e-06, "loss": 0.4103, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.23744762924388466, "learning_rate": 9.306394154079852e-06, "loss": 0.4151, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.26676930426740963, "learning_rate": 9.258645489465254e-06, "loss": 0.4171, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.23841784195844543, "learning_rate": 9.21098271243509e-06, "loss": 0.4035, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.23122286106775253, "learning_rate": 9.163406204099659e-06, "loss": 0.4074, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.24756688251733683, "learning_rate": 9.115916344879452e-06, "loss": 0.4091, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2486108503759705, "learning_rate": 9.068513514502126e-06, "loss": 0.4141, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2367199086103438, "learning_rate": 9.021198091999439e-06, "loss": 0.4056, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.276096156916934, "learning_rate": 8.973970455704251e-06, "loss": 0.3951, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.25219559552665444, "learning_rate": 8.926830983247495e-06, "loss": 0.3922, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.24233854992486736, "learning_rate": 8.879780051555116e-06, "loss": 0.402, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.24536086952522845, "learning_rate": 8.83281803684512e-06, "loss": 0.4112, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.23223135027022995, "learning_rate": 8.785945314624532e-06, "loss": 0.4109, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.22972114573747368, "learning_rate": 8.739162259686385e-06, "loss": 0.4024, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2607837358171502, "learning_rate": 8.692469246106734e-06, "loss": 0.4111, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.236335139068409, "learning_rate": 8.645866647241677e-06, "loss": 0.3975, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2643633636558213, "learning_rate": 8.599354835724348e-06, "loss": 0.409, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.24244804049683866, "learning_rate": 8.552934183461958e-06, "loss": 0.4064, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.21718336126903637, "learning_rate": 8.506605061632805e-06, "loss": 0.4038, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.24253843270882616, "learning_rate": 8.460367840683308e-06, "loss": 0.4088, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.251479204540659, "learning_rate": 8.414222890325065e-06, "loss": 0.4042, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.26787532247591095, "learning_rate": 8.368170579531855e-06, "loss": 0.4016, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.2626846849906404, "learning_rate": 8.322211276536733e-06, "loss": 0.4049, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.23939059386323133, "learning_rate": 8.27634534882907e-06, "loss": 0.3954, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.25049445959975297, "learning_rate": 8.230573163151585e-06, "loss": 0.3954, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.2527979578684752, "learning_rate": 8.184895085497466e-06, "loss": 0.3966, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.24218298067427602, "learning_rate": 8.139311481107401e-06, "loss": 0.4142, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.2578638646471765, "learning_rate": 8.093822714466686e-06, "loss": 0.4083, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2527956973125932, "learning_rate": 8.048429149302271e-06, "loss": 0.3972, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.23076476510111063, "learning_rate": 8.003131148579902e-06, "loss": 0.4086, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.22347767382317005, "learning_rate": 7.957929074501182e-06, "loss": 0.3999, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.23939158661380405, "learning_rate": 7.912823288500695e-06, "loss": 0.403, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.24192765922030346, "learning_rate": 7.867814151243102e-06, "loss": 0.4116, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2369084203474138, "learning_rate": 7.822902022620267e-06, "loss": 0.3912, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.2391007288229618, "learning_rate": 7.778087261748377e-06, "loss": 0.4037, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.24177804285569937, "learning_rate": 7.733370226965056e-06, "loss": 0.4046, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2537968938961793, "learning_rate": 7.688751275826527e-06, "loss": 0.3844, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.25798681089146475, "learning_rate": 7.644230765104735e-06, "loss": 0.404, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.24437999872468244, "learning_rate": 7.599809050784502e-06, "loss": 0.4049, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.24432624383010573, "learning_rate": 7.555486488060661e-06, "loss": 0.4089, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.22942436132480262, "learning_rate": 7.511263431335249e-06, "loss": 0.4161, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.23619732616807507, "learning_rate": 7.467140234214656e-06, "loss": 0.401, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.24606171398184207, "learning_rate": 7.423117249506777e-06, "loss": 0.4058, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.23700195342152566, "learning_rate": 7.379194829218231e-06, "loss": 0.4159, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.23738031117850406, "learning_rate": 7.335373324551518e-06, "loss": 0.3965, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.24636918484899473, "learning_rate": 7.291653085902224e-06, "loss": 0.4104, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2237211570970327, "learning_rate": 7.248034462856213e-06, "loss": 0.3935, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.24969183796672478, "learning_rate": 7.20451780418683e-06, "loss": 0.3988, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.23253618519562724, "learning_rate": 7.161103457852128e-06, "loss": 0.4103, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.21083366585558053, "learning_rate": 7.117791770992046e-06, "loss": 0.4075, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.24040584470353832, "learning_rate": 7.074583089925688e-06, "loss": 0.4017, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.23200967749802293, "learning_rate": 7.0314777601485155e-06, "loss": 0.41, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.22694909362094828, "learning_rate": 6.988476126329604e-06, "loss": 0.4012, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.22484328128876058, "learning_rate": 6.945578532308857e-06, "loss": 0.404, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.23513293544199815, "learning_rate": 6.902785321094301e-06, "loss": 0.3934, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.22486680373713436, "learning_rate": 6.8600968348593115e-06, "loss": 0.3941, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.21060392751470455, "learning_rate": 6.817513414939892e-06, "loss": 0.4023, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.23101604677833973, "learning_rate": 6.775035401831924e-06, "loss": 0.3868, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.222693451531927, "learning_rate": 6.732663135188473e-06, "loss": 0.4124, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.2293699036531189, "learning_rate": 6.690396953817055e-06, "loss": 0.4065, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.21207611836393597, "learning_rate": 6.648237195676927e-06, "loss": 0.4026, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.22288042667454158, "learning_rate": 6.606184197876395e-06, "loss": 0.3978, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.23086079924006356, "learning_rate": 6.564238296670109e-06, "loss": 0.3906, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2075248937482163, "learning_rate": 6.52239982745638e-06, "loss": 0.3995, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.22741322406314543, "learning_rate": 6.480669124774484e-06, "loss": 0.4111, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.22747534083961185, "learning_rate": 6.439046522302013e-06, "loss": 0.3999, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.2211764301586011, "learning_rate": 6.397532352852191e-06, "loss": 0.3971, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.234089103424579, "learning_rate": 6.356126948371202e-06, "loss": 0.4154, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.23792339414798508, "learning_rate": 6.314830639935559e-06, "loss": 0.3788, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.22701267422032706, "learning_rate": 6.273643757749448e-06, "loss": 0.4047, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.22678335181117118, "learning_rate": 6.2325666311420856e-06, "loss": 0.4041, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.22277135325260156, "learning_rate": 6.1915995885650675e-06, "loss": 0.3962, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.23487889801484746, "learning_rate": 6.150742957589784e-06, "loss": 0.3936, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.26002360745759745, "learning_rate": 6.109997064904774e-06, "loss": 0.4077, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.24362895932840847, "learning_rate": 6.069362236313092e-06, "loss": 0.406, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2239295443142911, "learning_rate": 6.0288387967297565e-06, "loss": 0.3935, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.25299769353963575, "learning_rate": 5.988427070179108e-06, "loss": 0.3949, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2454094555682382, "learning_rate": 5.948127379792234e-06, "loss": 0.4048, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.25654683804545664, "learning_rate": 5.90794004780439e-06, "loss": 0.3955, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.21419829831640083, "learning_rate": 5.867865395552405e-06, "loss": 0.4094, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.23199282425303144, "learning_rate": 5.8279037434721364e-06, "loss": 0.4069, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.244304052388769, "learning_rate": 5.788055411095892e-06, "loss": 0.4017, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.242924211667881, "learning_rate": 5.7483207170498625e-06, "loss": 0.4176, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.20650342461031274, "learning_rate": 5.708699979051613e-06, "loss": 0.3968, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2375032767573358, "learning_rate": 5.66919351390751e-06, "loss": 0.3983, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.2527182848938912, "learning_rate": 5.629801637510188e-06, "loss": 0.3864, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.255256980685137, "learning_rate": 5.590524664836043e-06, "loss": 0.3944, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.22116647268982093, "learning_rate": 5.551362909942708e-06, "loss": 0.4051, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.22338843882955703, "learning_rate": 5.51231668596653e-06, "loss": 0.4046, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.25443046253254836, "learning_rate": 5.47338630512007e-06, "loss": 0.4093, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.2827518247372822, "learning_rate": 5.434572078689617e-06, "loss": 0.4217, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.21498099312657412, "learning_rate": 5.395874317032694e-06, "loss": 0.4122, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.23446490992299568, "learning_rate": 5.357293329575573e-06, "loss": 0.4088, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.24718904774162426, "learning_rate": 5.318829424810797e-06, "loss": 0.416, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.21902485065624852, "learning_rate": 5.280482910294728e-06, "loss": 0.4071, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.21923682074667347, "learning_rate": 5.242254092645078e-06, "loss": 0.3914, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.22237005236061433, "learning_rate": 5.2041432775384445e-06, "loss": 0.4025, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.41138543971071645, "learning_rate": 5.166150769707892e-06, "loss": 0.4099, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.22464708285145762, "learning_rate": 5.128276872940503e-06, "loss": 0.4032, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.21337667182103653, "learning_rate": 5.090521890074953e-06, "loss": 0.4149, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.21996179278199504, "learning_rate": 5.0528861229990675e-06, "loss": 0.4128, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.20926423639717576, "learning_rate": 5.015369872647442e-06, "loss": 0.4132, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.211568745189015, "learning_rate": 4.9779734389990195e-06, "loss": 0.3999, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.2046086720520027, "learning_rate": 4.940697121074675e-06, "loss": 0.4108, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.21281875048973942, "learning_rate": 4.903541216934864e-06, "loss": 0.4042, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.2203770350369017, "learning_rate": 4.8665060236772e-06, "loss": 0.4002, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.22762746417604504, "learning_rate": 4.829591837434102e-06, "loss": 0.4023, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.2143924244766472, "learning_rate": 4.792798953370424e-06, "loss": 0.4117, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.21464401138288022, "learning_rate": 4.756127665681083e-06, "loss": 0.3996, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2100593127551032, "learning_rate": 4.719578267588725e-06, "loss": 0.4124, "step": 987 }, { "epoch": 4.0, "grad_norm": 1.5643810120376456, "learning_rate": 4.6831510513413525e-06, "loss": 0.397, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4551497353724431, "learning_rate": 4.6468463082100176e-06, "loss": 0.381, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.28973549188114006, "learning_rate": 4.610664328486485e-06, "loss": 0.3755, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.3178727665625032, "learning_rate": 4.5746054014809e-06, "loss": 0.36, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.45976158719808274, "learning_rate": 4.5386698155194766e-06, "loss": 0.3458, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3433164708245782, "learning_rate": 4.502857857942204e-06, "loss": 0.3631, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3177537835595129, "learning_rate": 4.467169815100549e-06, "loss": 0.3687, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.4049338617570676, "learning_rate": 4.431605972355137e-06, "loss": 0.3559, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.33631856782878405, "learning_rate": 4.396166614073516e-06, "loss": 0.3665, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.2587893422984394, "learning_rate": 4.360852023627846e-06, "loss": 0.3582, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3084042854811602, "learning_rate": 4.325662483392656e-06, "loss": 0.3578, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.3529456072389109, "learning_rate": 4.29059827474257e-06, "loss": 0.3618, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.32696911502448517, "learning_rate": 4.255659678050063e-06, "loss": 0.3739, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.2515362035489793, "learning_rate": 4.22084697268323e-06, "loss": 0.3664, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.2762380966066892, "learning_rate": 4.186160437003535e-06, "loss": 0.3615, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.30443747187165326, "learning_rate": 4.151600348363582e-06, "loss": 0.3598, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.26452881757765023, "learning_rate": 4.11716698310493e-06, "loss": 0.355, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.2305575966002573, "learning_rate": 4.082860616555848e-06, "loss": 0.3677, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.25319138490175574, "learning_rate": 4.048681523029125e-06, "loss": 0.3582, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.262779547614955, "learning_rate": 4.014629975819882e-06, "loss": 0.3548, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.25503349435368267, "learning_rate": 3.9807062472033855e-06, "loss": 0.3433, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.21485391533860446, "learning_rate": 3.94691060843287e-06, "loss": 0.3612, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.24271822515864439, "learning_rate": 3.913243329737353e-06, "loss": 0.3485, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.2467935233898316, "learning_rate": 3.879704680319503e-06, "loss": 0.3497, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.20956705160003214, "learning_rate": 3.846294928353471e-06, "loss": 0.357, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.21989116074328485, "learning_rate": 3.8130143409827345e-06, "loss": 0.3527, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2374186763825963, "learning_rate": 3.7798631843179887e-06, "loss": 0.372, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2299906513767461, "learning_rate": 3.7468417234349973e-06, "loss": 0.3515, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.21687557946956065, "learning_rate": 3.7139502223724823e-06, "loss": 0.3817, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.21510459040686172, "learning_rate": 3.6811889441300095e-06, "loss": 0.3461, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.22636197855045948, "learning_rate": 3.648558150665886e-06, "loss": 0.3602, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.22444801492135383, "learning_rate": 3.616058102895075e-06, "loss": 0.3696, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2118161217195509, "learning_rate": 3.583689060687079e-06, "loss": 0.3589, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.21652734177835037, "learning_rate": 3.5514512828639023e-06, "loss": 0.3618, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.21384360094822197, "learning_rate": 3.51934502719796e-06, "loss": 0.367, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.21513706793739967, "learning_rate": 3.4873705504100185e-06, "loss": 0.3544, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.21626398580342893, "learning_rate": 3.4555281081671345e-06, "loss": 0.3595, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.2203299334640632, "learning_rate": 3.4238179550806326e-06, "loss": 0.3449, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.22721907868174698, "learning_rate": 3.3922403447040497e-06, "loss": 0.3455, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.2131151174535051, "learning_rate": 3.3607955295311247e-06, "loss": 0.3555, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2085624807403298, "learning_rate": 3.32948376099375e-06, "loss": 0.3654, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.24808095820176235, "learning_rate": 3.2983052894599976e-06, "loss": 0.3581, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2071102197971234, "learning_rate": 3.2672603642320945e-06, "loss": 0.3652, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.20717239822262085, "learning_rate": 3.236349233544438e-06, "loss": 0.3645, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.21754130611959063, "learning_rate": 3.205572144561604e-06, "loss": 0.3488, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2150249822169925, "learning_rate": 3.174929343376374e-06, "loss": 0.3505, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2225081772979938, "learning_rate": 3.1444210750077777e-06, "loss": 0.3684, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2203664567486977, "learning_rate": 3.1140475833991046e-06, "loss": 0.3397, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.21960545425164474, "learning_rate": 3.0838091114159895e-06, "loss": 0.364, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.20720690325852512, "learning_rate": 3.0537059008444524e-06, "loss": 0.371, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.20683392725411365, "learning_rate": 3.0237381923889563e-06, "loss": 0.3621, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.21014444656026104, "learning_rate": 2.9939062256704997e-06, "loss": 0.3488, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.20106541304604322, "learning_rate": 2.964210239224696e-06, "loss": 0.3691, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.2118898473955646, "learning_rate": 2.934650470499869e-06, "loss": 0.3642, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.212448529908353, "learning_rate": 2.905227155855128e-06, "loss": 0.364, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.20937235548382618, "learning_rate": 2.875940530558519e-06, "loss": 0.3456, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2090163829899654, "learning_rate": 2.8467908287851154e-06, "loss": 0.3545, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.20865134001428567, "learning_rate": 2.8177782836151603e-06, "loss": 0.3506, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2191563948281825, "learning_rate": 2.7889031270321874e-06, "loss": 0.3233, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.20612515155251204, "learning_rate": 2.760165589921184e-06, "loss": 0.3571, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.20834940812026786, "learning_rate": 2.7315659020667305e-06, "loss": 0.3476, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21014656212197408, "learning_rate": 2.703104292151164e-06, "loss": 0.353, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.21440309859816215, "learning_rate": 2.6747809877527607e-06, "loss": 0.3474, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.20544662506214822, "learning_rate": 2.6465962153439082e-06, "loss": 0.3596, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.2200335001582436, "learning_rate": 2.618550200289303e-06, "loss": 0.3532, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.20554462422520048, "learning_rate": 2.59064316684412e-06, "loss": 0.3706, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20677145210138276, "learning_rate": 2.562875338152264e-06, "loss": 0.3376, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.21423084792358474, "learning_rate": 2.5352469362445552e-06, "loss": 0.3452, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.21443221142025357, "learning_rate": 2.5077581820369523e-06, "loss": 0.3653, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.21708769493113453, "learning_rate": 2.480409295328803e-06, "loss": 0.3487, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.22949768173971177, "learning_rate": 2.45320049480108e-06, "loss": 0.3393, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.20924864321327602, "learning_rate": 2.4261319980146293e-06, "loss": 0.3595, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.21139491118720588, "learning_rate": 2.399204021408421e-06, "loss": 0.3526, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.20580452296238005, "learning_rate": 2.3724167802978395e-06, "loss": 0.3646, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.20632523403270284, "learning_rate": 2.3457704888729625e-06, "loss": 0.3577, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.21428247614653023, "learning_rate": 2.3192653601968162e-06, "loss": 0.3703, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.20151479543108283, "learning_rate": 2.2929016062037057e-06, "loss": 0.3647, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2099604421115424, "learning_rate": 2.2666794376975055e-06, "loss": 0.3633, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.20445608060890585, "learning_rate": 2.24059906434998e-06, "loss": 0.3533, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.21565516842814939, "learning_rate": 2.214660694699091e-06, "loss": 0.3496, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.2188652182892837, "learning_rate": 2.188864536147355e-06, "loss": 0.3434, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2049075410103995, "learning_rate": 2.1632107949601757e-06, "loss": 0.3563, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2119184901561791, "learning_rate": 2.137699676264171e-06, "loss": 0.3626, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.21125285042690026, "learning_rate": 2.1123313840455738e-06, "loss": 0.3691, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.2094683813070417, "learning_rate": 2.08710612114857e-06, "loss": 0.3529, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.20660166623525775, "learning_rate": 2.0620240892736953e-06, "loss": 0.3473, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.21249337184711461, "learning_rate": 2.0370854889762e-06, "loss": 0.3614, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.20393925018747208, "learning_rate": 2.0122905196644726e-06, "loss": 0.3547, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21531701011246984, "learning_rate": 1.987639379598427e-06, "loss": 0.3595, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.20071883166020432, "learning_rate": 1.963132265887919e-06, "loss": 0.3588, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20518786553008964, "learning_rate": 1.9387693744911784e-06, "loss": 0.3622, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.2040814830436772, "learning_rate": 1.9145509002132368e-06, "loss": 0.3636, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.22089340688083106, "learning_rate": 1.8904770367043723e-06, "loss": 0.3397, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.21048118691610726, "learning_rate": 1.8665479764585504e-06, "loss": 0.3403, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.20014960996168324, "learning_rate": 1.8427639108118977e-06, "loss": 0.3544, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.20645953802321365, "learning_rate": 1.8191250299411755e-06, "loss": 0.3576, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.20774225291771334, "learning_rate": 1.7956315228622446e-06, "loss": 0.374, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2089112481008161, "learning_rate": 1.7722835774285553e-06, "loss": 0.3709, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2087298108400787, "learning_rate": 1.7490813803296624e-06, "loss": 0.3407, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.20527814791293328, "learning_rate": 1.726025117089718e-06, "loss": 0.3641, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.20599306413675314, "learning_rate": 1.70311497206598e-06, "loss": 0.3472, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2024418061259123, "learning_rate": 1.6803511284473638e-06, "loss": 0.366, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.20797033803490658, "learning_rate": 1.6577337682529538e-06, "loss": 0.3616, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.20987590016166507, "learning_rate": 1.6352630723305617e-06, "loss": 0.3585, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.21591721162875402, "learning_rate": 1.612939220355272e-06, "loss": 0.3492, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.20492796277883144, "learning_rate": 1.5907623908280112e-06, "loss": 0.3449, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2191704635252419, "learning_rate": 1.568732761074121e-06, "loss": 0.3563, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.2072224584277642, "learning_rate": 1.5468505072419237e-06, "loss": 0.3549, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.1995048851614893, "learning_rate": 1.5251158043013448e-06, "loss": 0.3642, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2084274529841397, "learning_rate": 1.5035288260424885e-06, "loss": 0.352, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.20644664326904233, "learning_rate": 1.4820897450742623e-06, "loss": 0.3502, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.21247868278363502, "learning_rate": 1.4607987328229767e-06, "loss": 0.3501, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.20224479042584004, "learning_rate": 1.4396559595310056e-06, "loss": 0.356, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2037808730401735, "learning_rate": 1.4186615942553973e-06, "loss": 0.3589, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.19741840263098215, "learning_rate": 1.3978158048665424e-06, "loss": 0.3575, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.20534848182880897, "learning_rate": 1.3771187580468115e-06, "loss": 0.3701, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.20155080856977145, "learning_rate": 1.3565706192892392e-06, "loss": 0.3532, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.20258495091537496, "learning_rate": 1.3361715528961993e-06, "loss": 0.3416, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.20660896691017006, "learning_rate": 1.3159217219780817e-06, "loss": 0.3462, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.19699182936616488, "learning_rate": 1.2958212884519949e-06, "loss": 0.3602, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.20081771815243785, "learning_rate": 1.2758704130404675e-06, "loss": 0.376, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.20116535660048696, "learning_rate": 1.2560692552701738e-06, "loss": 0.3534, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.19808148521367785, "learning_rate": 1.2364179734706382e-06, "loss": 0.3719, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.20266234899180022, "learning_rate": 1.2169167247729852e-06, "loss": 0.3594, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2063614673176125, "learning_rate": 1.1975656651086864e-06, "loss": 0.3548, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.1996526459828305, "learning_rate": 1.1783649492082926e-06, "loss": 0.3479, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.1990281313503341, "learning_rate": 1.1593147306002183e-06, "loss": 0.3695, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2066401125137327, "learning_rate": 1.140415161609505e-06, "loss": 0.3669, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2049125244525772, "learning_rate": 1.121666393356604e-06, "loss": 0.3707, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.20311618715706037, "learning_rate": 1.1030685757561632e-06, "loss": 0.3618, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2012364504220285, "learning_rate": 1.0846218575158373e-06, "loss": 0.3721, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.199902891408482, "learning_rate": 1.066326386135097e-06, "loss": 0.363, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.20124354534436784, "learning_rate": 1.0481823079040398e-06, "loss": 0.3636, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.19757825360728062, "learning_rate": 1.0301897679022344e-06, "loss": 0.366, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.1989267244369639, "learning_rate": 1.0123489099975491e-06, "loss": 0.3752, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2086607242314458, "learning_rate": 9.9465987684501e-07, "loss": 0.346, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.19903039578010204, "learning_rate": 9.771228098856534e-07, "loss": 0.3577, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.19385869646300674, "learning_rate": 9.597378493454013e-07, "loss": 0.3697, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.20546346803672255, "learning_rate": 9.425051342339353e-07, "loss": 0.3574, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.20399309872750365, "learning_rate": 9.254248023435864e-07, "loss": 0.3566, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.21157421577030042, "learning_rate": 9.084969902482288e-07, "loss": 0.3411, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.2005350409581637, "learning_rate": 8.917218333021993e-07, "loss": 0.3737, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2007969086780529, "learning_rate": 8.750994656392109e-07, "loss": 0.3577, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.20653476508579888, "learning_rate": 8.58630020171265e-07, "loss": 0.3506, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2068474222425081, "learning_rate": 8.423136285876099e-07, "loss": 0.3563, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.20224932425977601, "learning_rate": 8.26150421353682e-07, "loss": 0.3637, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.20419855318918306, "learning_rate": 8.101405277100549e-07, "loss": 0.3614, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.20910897011982968, "learning_rate": 7.942840756714077e-07, "loss": 0.3399, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.19928649813003319, "learning_rate": 7.785811920255093e-07, "loss": 0.3652, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.20216338782112875, "learning_rate": 7.630320023322024e-07, "loss": 0.3599, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.20638779786858205, "learning_rate": 7.476366309223903e-07, "loss": 0.3566, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.21285126028723483, "learning_rate": 7.323952008970537e-07, "loss": 0.3454, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.19777549054283147, "learning_rate": 7.173078341262618e-07, "loss": 0.3612, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2006194793652339, "learning_rate": 7.023746512481989e-07, "loss": 0.3694, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2055391175700939, "learning_rate": 6.875957716681902e-07, "loss": 0.3689, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.21500911192138383, "learning_rate": 6.729713135577687e-07, "loss": 0.356, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2159873642619422, "learning_rate": 6.585013938537143e-07, "loss": 0.34, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.20533251843911307, "learning_rate": 6.441861282571115e-07, "loss": 0.3578, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.20275720928781105, "learning_rate": 6.300256312324471e-07, "loss": 0.3449, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.20183660337111223, "learning_rate": 6.160200160066776e-07, "loss": 0.3497, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.20854523857795762, "learning_rate": 6.021693945683327e-07, "loss": 0.3519, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.2064182787639374, "learning_rate": 5.884738776666044e-07, "loss": 0.3515, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.1995772020735769, "learning_rate": 5.749335748104878e-07, "loss": 0.3521, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.194507691850203, "learning_rate": 5.615485942678778e-07, "loss": 0.365, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.199291091381774, "learning_rate": 5.483190430647289e-07, "loss": 0.3493, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.20135097453810696, "learning_rate": 5.352450269841747e-07, "loss": 0.3566, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.20926833343758794, "learning_rate": 5.22326650565701e-07, "loss": 0.364, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.20604521372952242, "learning_rate": 5.095640171043048e-07, "loss": 0.3642, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.19440918224769765, "learning_rate": 4.969572286496594e-07, "loss": 0.3524, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.2205191791338185, "learning_rate": 4.845063860053079e-07, "loss": 0.3301, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.1972025506985137, "learning_rate": 4.7221158872785997e-07, "loss": 0.356, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.19349189063122837, "learning_rate": 4.600729351261857e-07, "loss": 0.3437, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.1956744513350584, "learning_rate": 4.4809052226063355e-07, "loss": 0.3792, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.19810164594333726, "learning_rate": 4.3626444594226046e-07, "loss": 0.3556, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2038590758503468, "learning_rate": 4.245948007320588e-07, "loss": 0.343, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.19451983444923346, "learning_rate": 4.130816799401971e-07, "loss": 0.3709, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.2047545879779555, "learning_rate": 4.017251756252827e-07, "loss": 0.3614, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.2036411421766865, "learning_rate": 3.9052537859362473e-07, "loss": 0.3576, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.20594254098920003, "learning_rate": 3.7948237839849687e-07, "loss": 0.3544, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.21526310056656361, "learning_rate": 3.6859626333943797e-07, "loss": 0.3698, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.1939427368395082, "learning_rate": 3.578671204615347e-07, "loss": 0.3554, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.2093482012435113, "learning_rate": 3.472950355547267e-07, "loss": 0.3539, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.20412782250294798, "learning_rate": 3.3688009315312244e-07, "loss": 0.3514, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.20423482657137698, "learning_rate": 3.266223765343224e-07, "loss": 0.3646, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.20161649437791893, "learning_rate": 3.16521967718757e-07, "loss": 0.3453, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.19942063375030325, "learning_rate": 3.0657894746902726e-07, "loss": 0.3715, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.19628187594776772, "learning_rate": 2.9679339528925654e-07, "loss": 0.3703, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.1932829277880981, "learning_rate": 2.871653894244597e-07, "loss": 0.35, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.20118679813310833, "learning_rate": 2.7769500685991266e-07, "loss": 0.3604, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.19594133757375876, "learning_rate": 2.683823233205485e-07, "loss": 0.3602, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.19815767572175882, "learning_rate": 2.592274132703287e-07, "loss": 0.3665, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.19846816430013756, "learning_rate": 2.502303499116754e-07, "loss": 0.3547, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.20159437070620653, "learning_rate": 2.413912051848666e-07, "loss": 0.3565, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.19611034681225564, "learning_rate": 2.3271004976746613e-07, "loss": 0.3649, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.1975419385327038, "learning_rate": 2.2418695307376393e-07, "loss": 0.376, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.1954087744309306, "learning_rate": 2.1582198325420968e-07, "loss": 0.3652, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.1956399614422869, "learning_rate": 2.0761520719488447e-07, "loss": 0.3595, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.20111725788233087, "learning_rate": 1.9956669051694798e-07, "loss": 0.3479, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.24071459577526588, "learning_rate": 1.916764975761254e-07, "loss": 0.3478, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.19794789566654786, "learning_rate": 1.839446914621923e-07, "loss": 0.3518, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.19194408545839386, "learning_rate": 1.7637133399845962e-07, "loss": 0.3561, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.20619277768519628, "learning_rate": 1.6895648574129397e-07, "loss": 0.3595, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2024805859324051, "learning_rate": 1.6170020597962465e-07, "loss": 0.3493, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.19733531684657601, "learning_rate": 1.5460255273447078e-07, "loss": 0.3578, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.1934239828045934, "learning_rate": 1.4766358275847715e-07, "loss": 0.3704, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.21253386314602538, "learning_rate": 1.4088335153546573e-07, "loss": 0.3779, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.19899395896214778, "learning_rate": 1.3426191327998496e-07, "loss": 0.3502, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.20232799851761568, "learning_rate": 1.277993209368744e-07, "loss": 0.3558, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.19973782344615046, "learning_rate": 1.214956261808542e-07, "loss": 0.3433, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.19817740953256568, "learning_rate": 1.1535087941609846e-07, "loss": 0.3677, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.19717696510401087, "learning_rate": 1.0936512977583802e-07, "loss": 0.3615, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.20374549583561016, "learning_rate": 1.0353842512196732e-07, "loss": 0.3566, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.19198731795942744, "learning_rate": 9.787081204466253e-08, "loss": 0.3798, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.1995719947901251, "learning_rate": 9.236233586200627e-08, "loss": 0.3536, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.20582347693398118, "learning_rate": 8.70130406196279e-08, "loss": 0.3684, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2016924727226356, "learning_rate": 8.182296909035047e-08, "loss": 0.3586, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.19521432768870894, "learning_rate": 7.679216277384439e-08, "loss": 0.3619, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.19224123200014084, "learning_rate": 7.19206618963053e-08, "loss": 0.3628, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.19731192739106507, "learning_rate": 6.720850541012347e-08, "loss": 0.3753, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.20077234969350946, "learning_rate": 6.265573099357714e-08, "loss": 0.3743, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.19545780704099713, "learning_rate": 5.826237505053067e-08, "loss": 0.3469, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.20047732535826582, "learning_rate": 5.4028472710137e-08, "loss": 0.3407, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.20181119499638073, "learning_rate": 4.9954057826571146e-08, "loss": 0.3421, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.20428412871119817, "learning_rate": 4.6039162978743776e-08, "loss": 0.3596, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.1997471897397217, "learning_rate": 4.228381947004812e-08, "loss": 0.3526, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.1990597906854231, "learning_rate": 3.868805732811343e-08, "loss": 0.353, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.19308497568616914, "learning_rate": 3.525190530455636e-08, "loss": 0.358, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.19658026373514095, "learning_rate": 3.197539087475887e-08, "loss": 0.3522, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.19791087591900697, "learning_rate": 2.8858540237641786e-08, "loss": 0.3691, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.20257141260117636, "learning_rate": 2.5901378315458247e-08, "loss": 0.3688, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.1966390040015413, "learning_rate": 2.3103928753598347e-08, "loss": 0.3589, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.19905044482709247, "learning_rate": 2.0466213920393718e-08, "loss": 0.3538, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.1973885920032489, "learning_rate": 1.7988254906942115e-08, "loss": 0.3604, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.18621480483544994, "learning_rate": 1.5670071526936447e-08, "loss": 0.3687, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.19800145027497418, "learning_rate": 1.3511682316509344e-08, "loss": 0.3504, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.19635439075414254, "learning_rate": 1.1513104534086605e-08, "loss": 0.3596, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.1974507833497752, "learning_rate": 9.67435416023843e-09, "loss": 0.3696, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.2040618485516086, "learning_rate": 7.995445897566178e-09, "loss": 0.3531, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.1960961805552175, "learning_rate": 6.476393170578021e-09, "loss": 0.3513, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.21337053107879922, "learning_rate": 5.11720812557348e-09, "loss": 0.3281, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.20283528404661222, "learning_rate": 3.917901630563492e-09, "loss": 0.3388, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.1946474059869895, "learning_rate": 2.878483275170485e-09, "loss": 0.3583, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.18975686070978512, "learning_rate": 1.998961370555108e-09, "loss": 0.3565, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.2049186264657594, "learning_rate": 1.2793429493518361e-09, "loss": 0.3468, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.19054043513488006, "learning_rate": 7.196337656112384e-10, "loss": 0.3688, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.19228534028077005, "learning_rate": 3.198382947511292e-10, "loss": 0.3661, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.19212737108713365, "learning_rate": 7.995973352770137e-11, "loss": 0.3629, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19751168383582812, "learning_rate": 0.0, "loss": 0.3538, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 4.89495172215944e+18, "train_loss": 0.4867687714727301, "train_runtime": 29333.1196, "train_samples_per_second": 5.386, "train_steps_per_second": 0.042 } ], "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": 4.89495172215944e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }