{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 7.024099833639059, "learning_rate": 3.2258064516129035e-07, "loss": 0.9909, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 7.219482706468752, "learning_rate": 6.451612903225807e-07, "loss": 1.0309, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.037021120964979, "learning_rate": 9.67741935483871e-07, "loss": 1.0087, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 7.218604775825959, "learning_rate": 1.2903225806451614e-06, "loss": 1.0183, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.5057351859713, "learning_rate": 1.6129032258064516e-06, "loss": 0.9734, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.4171757556555855, "learning_rate": 1.935483870967742e-06, "loss": 0.9879, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.0097094904607244, "learning_rate": 2.2580645161290324e-06, "loss": 0.964, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.516704872882486, "learning_rate": 2.580645161290323e-06, "loss": 0.9487, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.264218365714318, "learning_rate": 2.903225806451613e-06, "loss": 0.8947, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.1653957146964573, "learning_rate": 3.225806451612903e-06, "loss": 0.9023, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.141541885460376, "learning_rate": 3.548387096774194e-06, "loss": 0.8858, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.556314539513641, "learning_rate": 3.870967741935484e-06, "loss": 0.9083, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.826551125846962, "learning_rate": 4.193548387096774e-06, "loss": 0.8934, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.523501198442618, "learning_rate": 4.516129032258065e-06, "loss": 0.8623, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.3587516563759525, "learning_rate": 4.838709677419355e-06, "loss": 0.8704, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.1695380813682097, "learning_rate": 5.161290322580646e-06, "loss": 0.8447, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.9278599349739505, "learning_rate": 5.483870967741935e-06, "loss": 0.8472, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.5520363416237046, "learning_rate": 5.806451612903226e-06, "loss": 0.8499, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.050231136764055, "learning_rate": 6.129032258064517e-06, "loss": 0.8095, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.8061813853931243, "learning_rate": 6.451612903225806e-06, "loss": 0.7776, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.5101764589961875, "learning_rate": 6.774193548387097e-06, "loss": 0.7823, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.5584172937933474, "learning_rate": 7.096774193548388e-06, "loss": 0.8067, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.471541269118232, "learning_rate": 7.4193548387096784e-06, "loss": 0.7661, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.2658699589868432, "learning_rate": 7.741935483870968e-06, "loss": 0.7642, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.04711002485056, "learning_rate": 8.064516129032258e-06, "loss": 0.7728, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.8577449032923617, "learning_rate": 8.387096774193549e-06, "loss": 0.7436, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.8635467709761473, "learning_rate": 8.70967741935484e-06, "loss": 0.7363, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.9208621428301048, "learning_rate": 9.03225806451613e-06, "loss": 0.7593, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7524136864260029, "learning_rate": 9.35483870967742e-06, "loss": 0.7286, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7910532009058218, "learning_rate": 9.67741935483871e-06, "loss": 0.7357, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6696518592678488, "learning_rate": 1e-05, "loss": 0.7439, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.6535822252042823, "learning_rate": 1.0322580645161291e-05, "loss": 0.7048, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7024248121735, "learning_rate": 1.0645161290322582e-05, "loss": 0.7291, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.6921807803667479, "learning_rate": 1.096774193548387e-05, "loss": 0.7291, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.655826395968062, "learning_rate": 1.1290322580645164e-05, "loss": 0.7077, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.5811509927903458, "learning_rate": 1.1612903225806453e-05, "loss": 0.7185, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5524609458100024, "learning_rate": 1.1935483870967743e-05, "loss": 0.7046, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6538575889034216, "learning_rate": 1.2258064516129034e-05, "loss": 0.7241, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.6141183239673167, "learning_rate": 1.2580645161290324e-05, "loss": 0.7013, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5607284080423153, "learning_rate": 1.2903225806451613e-05, "loss": 0.6911, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.6550718547650525, "learning_rate": 1.3225806451612903e-05, "loss": 0.7059, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5078882144390476, "learning_rate": 1.3548387096774194e-05, "loss": 0.7097, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5602860701932264, "learning_rate": 1.3870967741935486e-05, "loss": 0.674, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.4833872402674177, "learning_rate": 1.4193548387096776e-05, "loss": 0.7008, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.5236642831100674, "learning_rate": 1.4516129032258066e-05, "loss": 0.6988, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.4949740517361925, "learning_rate": 1.4838709677419357e-05, "loss": 0.6754, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.5124296354678916, "learning_rate": 1.5161290322580646e-05, "loss": 0.6925, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.45031979312988407, "learning_rate": 1.5483870967741936e-05, "loss": 0.6636, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5180692676137474, "learning_rate": 1.5806451612903226e-05, "loss": 0.6713, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.5238956785448731, "learning_rate": 1.6129032258064517e-05, "loss": 0.6938, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5697537309983138, "learning_rate": 1.6451612903225807e-05, "loss": 0.6862, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.4958104035157216, "learning_rate": 1.6774193548387098e-05, "loss": 0.6963, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.4949636420514614, "learning_rate": 1.7096774193548388e-05, "loss": 0.6773, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.4984073430663148, "learning_rate": 1.741935483870968e-05, "loss": 0.6947, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.5496678510687758, "learning_rate": 1.774193548387097e-05, "loss": 0.6647, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.5642720382195154, "learning_rate": 1.806451612903226e-05, "loss": 0.7055, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.663262805254893, "learning_rate": 1.838709677419355e-05, "loss": 0.6778, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.77579901686445, "learning_rate": 1.870967741935484e-05, "loss": 0.6789, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.640253536145152, "learning_rate": 1.903225806451613e-05, "loss": 0.6808, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.8961972120859654, "learning_rate": 1.935483870967742e-05, "loss": 0.6686, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5706706140594988, "learning_rate": 1.967741935483871e-05, "loss": 0.6683, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.6797696648391035, "learning_rate": 2e-05, "loss": 0.6581, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.592479662972866, "learning_rate": 2.0322580645161292e-05, "loss": 0.657, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.6926906556753626, "learning_rate": 2.0645161290322582e-05, "loss": 0.6655, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.6027577603726819, "learning_rate": 2.0967741935483873e-05, "loss": 0.6821, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6943458406482084, "learning_rate": 2.1290322580645163e-05, "loss": 0.6624, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7749861684885332, "learning_rate": 2.161290322580645e-05, "loss": 0.6595, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.6346059922516201, "learning_rate": 2.193548387096774e-05, "loss": 0.6891, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.8111818169241996, "learning_rate": 2.225806451612903e-05, "loss": 0.6827, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.8924337996355128, "learning_rate": 2.2580645161290328e-05, "loss": 0.6614, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.5934674703869932, "learning_rate": 2.2903225806451615e-05, "loss": 0.6535, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.8733276488765587, "learning_rate": 2.3225806451612906e-05, "loss": 0.6592, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.904637626967447, "learning_rate": 2.3548387096774196e-05, "loss": 0.6695, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.9400912958647425, "learning_rate": 2.3870967741935486e-05, "loss": 0.6498, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.8646582712426943, "learning_rate": 2.4193548387096777e-05, "loss": 0.6722, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.8662357012021561, "learning_rate": 2.4516129032258067e-05, "loss": 0.6701, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.0224089455367191, "learning_rate": 2.4838709677419358e-05, "loss": 0.6806, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 1.0386714954152685, "learning_rate": 2.5161290322580648e-05, "loss": 0.6637, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.9055683069412006, "learning_rate": 2.548387096774194e-05, "loss": 0.6847, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.761437144634681, "learning_rate": 2.5806451612903226e-05, "loss": 0.6579, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.705817908658778, "learning_rate": 2.6129032258064516e-05, "loss": 0.653, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.6723740861231169, "learning_rate": 2.6451612903225806e-05, "loss": 0.6656, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.9215680059306989, "learning_rate": 2.6774193548387097e-05, "loss": 0.6307, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.908917144903534, "learning_rate": 2.7096774193548387e-05, "loss": 0.6724, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.7969679543728462, "learning_rate": 2.7419354838709678e-05, "loss": 0.6584, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7988487147680999, "learning_rate": 2.774193548387097e-05, "loss": 0.6509, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.806686182339772, "learning_rate": 2.8064516129032262e-05, "loss": 0.6642, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.9482858181241922, "learning_rate": 2.8387096774193552e-05, "loss": 0.6271, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.795780680440375, "learning_rate": 2.8709677419354843e-05, "loss": 0.6368, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7553729510791841, "learning_rate": 2.9032258064516133e-05, "loss": 0.6549, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.9744003551627839, "learning_rate": 2.9354838709677423e-05, "loss": 0.6632, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.9992686382823521, "learning_rate": 2.9677419354838714e-05, "loss": 0.6708, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.5966080494443489, "learning_rate": 3.0000000000000004e-05, "loss": 0.6685, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.8232471011235541, "learning_rate": 3.032258064516129e-05, "loss": 0.6615, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.9337084876637858, "learning_rate": 3.0645161290322585e-05, "loss": 0.669, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.1935775710411558, "learning_rate": 3.096774193548387e-05, "loss": 0.6752, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.8085010375414077, "learning_rate": 3.1290322580645166e-05, "loss": 0.6619, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.1957089694445284, "learning_rate": 3.161290322580645e-05, "loss": 0.6591, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.8197948545047065, "learning_rate": 3.193548387096774e-05, "loss": 0.6599, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.9208215839797048, "learning_rate": 3.2258064516129034e-05, "loss": 0.66, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.1503957121054023, "learning_rate": 3.258064516129033e-05, "loss": 0.6709, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.6346553170861475, "learning_rate": 3.2903225806451614e-05, "loss": 0.6377, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.9309155282538786, "learning_rate": 3.322580645161291e-05, "loss": 0.644, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.8666089550515694, "learning_rate": 3.3548387096774195e-05, "loss": 0.6508, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.0280467698156213, "learning_rate": 3.387096774193549e-05, "loss": 0.6433, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.9506055113769326, "learning_rate": 3.4193548387096776e-05, "loss": 0.6737, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.9566886240182865, "learning_rate": 3.451612903225807e-05, "loss": 0.6351, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.250711699811772, "learning_rate": 3.483870967741936e-05, "loss": 0.6724, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.7752389812958109, "learning_rate": 3.516129032258065e-05, "loss": 0.645, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.8655604617508671, "learning_rate": 3.548387096774194e-05, "loss": 0.6436, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.9317897050237793, "learning_rate": 3.5806451612903225e-05, "loss": 0.6421, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8337326316930952, "learning_rate": 3.612903225806452e-05, "loss": 0.6656, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.5780323210602688, "learning_rate": 3.6451612903225805e-05, "loss": 0.6563, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.0310166466912654, "learning_rate": 3.67741935483871e-05, "loss": 0.658, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.122779300090675, "learning_rate": 3.7096774193548386e-05, "loss": 0.6453, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6053463922882715, "learning_rate": 3.741935483870968e-05, "loss": 0.6678, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.9194518984413748, "learning_rate": 3.7741935483870974e-05, "loss": 0.6456, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.9495486353856258, "learning_rate": 3.806451612903226e-05, "loss": 0.6371, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.8651678245655214, "learning_rate": 3.8387096774193555e-05, "loss": 0.6528, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.9031138200111835, "learning_rate": 3.870967741935484e-05, "loss": 0.6482, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.6053364321580867, "learning_rate": 3.9032258064516135e-05, "loss": 0.6582, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.7252400831049957, "learning_rate": 3.935483870967742e-05, "loss": 0.6537, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.8871571332164597, "learning_rate": 3.9677419354838716e-05, "loss": 0.6439, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.1131326879726278, "learning_rate": 4e-05, "loss": 0.6585, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.9820721594269142, "learning_rate": 3.9999920040266474e-05, "loss": 0.6539, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.011102373653673, "learning_rate": 3.999968016170525e-05, "loss": 0.6726, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.0108546449496665, "learning_rate": 3.9999280366234394e-05, "loss": 0.6567, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.159432863585279, "learning_rate": 3.999872065705065e-05, "loss": 0.6704, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.8681300294547739, "learning_rate": 3.999800103862945e-05, "loss": 0.6428, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6844747868502553, "learning_rate": 3.9997121516724834e-05, "loss": 0.6533, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.793056193457485, "learning_rate": 3.999608209836944e-05, "loss": 0.647, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.0709645962229015, "learning_rate": 3.999488279187443e-05, "loss": 0.6616, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 1.0239362886528567, "learning_rate": 3.9993523606829425e-05, "loss": 0.6479, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7691777752667378, "learning_rate": 3.9992004554102435e-05, "loss": 0.631, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7251826741598798, "learning_rate": 3.999032564583976e-05, "loss": 0.6585, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.0888191977296087, "learning_rate": 3.998848689546591e-05, "loss": 0.6652, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7522021803472644, "learning_rate": 3.9986488317683496e-05, "loss": 0.6289, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.8033999306726254, "learning_rate": 3.9984329928473067e-05, "loss": 0.6576, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.8006462666329607, "learning_rate": 3.998201174509306e-05, "loss": 0.6449, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6017070522477647, "learning_rate": 3.997953378607961e-05, "loss": 0.6533, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.7014482295576706, "learning_rate": 3.9976896071246403e-05, "loss": 0.6419, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.6927138508057262, "learning_rate": 3.997409862168454e-05, "loss": 0.6375, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.5101411969971064, "learning_rate": 3.997114145976237e-05, "loss": 0.6213, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5454676940181437, "learning_rate": 3.9968024609125245e-05, "loss": 0.6402, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6483419427477424, "learning_rate": 3.996474809469545e-05, "loss": 0.6282, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.4953108047168988, "learning_rate": 3.996131194267189e-05, "loss": 0.6325, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.6542446637095772, "learning_rate": 3.995771618052995e-05, "loss": 0.622, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.632015416203537, "learning_rate": 3.9953960837021256e-05, "loss": 0.6561, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.6306675710597494, "learning_rate": 3.995004594217343e-05, "loss": 0.63, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6694722317620192, "learning_rate": 3.994597152728987e-05, "loss": 0.6367, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6954769967936154, "learning_rate": 3.994173762494947e-05, "loss": 0.628, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.708246370943644, "learning_rate": 3.9937344269006424e-05, "loss": 0.6519, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.5743086796956827, "learning_rate": 3.993279149458988e-05, "loss": 0.6541, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.7248761735244029, "learning_rate": 3.9928079338103695e-05, "loss": 0.6512, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.6703793002595275, "learning_rate": 3.992320783722616e-05, "loss": 0.6432, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7749638085206274, "learning_rate": 3.991817703090965e-05, "loss": 0.6524, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.763019221919119, "learning_rate": 3.991298695938038e-05, "loss": 0.6232, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6084832776455782, "learning_rate": 3.9907637664138e-05, "loss": 0.6394, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7364547388787909, "learning_rate": 3.990212918795534e-05, "loss": 0.6193, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.5750837411958605, "learning_rate": 3.9896461574878036e-05, "loss": 0.658, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.7243550863408237, "learning_rate": 3.989063487022416e-05, "loss": 0.6295, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5939919513498555, "learning_rate": 3.9884649120583903e-05, "loss": 0.6323, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.576184449657782, "learning_rate": 3.987850437381915e-05, "loss": 0.6449, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.5882706840081634, "learning_rate": 3.987220067906313e-05, "loss": 0.6477, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.5485116467455841, "learning_rate": 3.986573808672002e-05, "loss": 0.6559, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.539574781029532, "learning_rate": 3.9859116648464534e-05, "loss": 0.6242, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5685747068381412, "learning_rate": 3.985233641724152e-05, "loss": 0.651, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.4854374346171153, "learning_rate": 3.984539744726554e-05, "loss": 0.6287, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.5987470171706325, "learning_rate": 3.983829979402038e-05, "loss": 0.6208, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.46132313298817046, "learning_rate": 3.983104351425871e-05, "loss": 0.6249, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6938237827321425, "learning_rate": 3.982362866600154e-05, "loss": 0.6338, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.4948857955680586, "learning_rate": 3.9816055308537806e-05, "loss": 0.6421, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.5959851209773042, "learning_rate": 3.980832350242388e-05, "loss": 0.6367, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.6262545573225795, "learning_rate": 3.980043330948306e-05, "loss": 0.6336, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.501328838625356, "learning_rate": 3.9792384792805124e-05, "loss": 0.6312, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.7584338370805351, "learning_rate": 3.978417801674579e-05, "loss": 0.6108, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.586564273997992, "learning_rate": 3.9775813046926244e-05, "loss": 0.6543, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6037599846661973, "learning_rate": 3.976728995023254e-05, "loss": 0.6512, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.5481572875923656, "learning_rate": 3.975860879481514e-05, "loss": 0.6437, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.5004612638896249, "learning_rate": 3.974976965008833e-05, "loss": 0.6482, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5260949456203861, "learning_rate": 3.9740772586729674e-05, "loss": 0.6567, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.6999117163634039, "learning_rate": 3.973161767667946e-05, "loss": 0.6386, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6528609392136817, "learning_rate": 3.972230499314009e-05, "loss": 0.6284, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.5104096030280326, "learning_rate": 3.9712834610575545e-05, "loss": 0.6446, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5424073220920137, "learning_rate": 3.9703206604710746e-05, "loss": 0.6293, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.5307641052617306, "learning_rate": 3.969342105253098e-05, "loss": 0.6471, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.5806691137057095, "learning_rate": 3.9683478032281246e-05, "loss": 0.6497, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5604413153038406, "learning_rate": 3.967337762346568e-05, "loss": 0.618, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.5246224039694894, "learning_rate": 3.9663119906846885e-05, "loss": 0.6343, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.43904867207076254, "learning_rate": 3.965270496444528e-05, "loss": 0.6231, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.47931424383170185, "learning_rate": 3.9642132879538465e-05, "loss": 0.6395, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.4407460635875649, "learning_rate": 3.9631403736660566e-05, "loss": 0.6291, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.47241886949251016, "learning_rate": 3.962051762160151e-05, "loss": 0.633, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.4755788467496921, "learning_rate": 3.960947462140638e-05, "loss": 0.6375, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5328207203324675, "learning_rate": 3.959827482437472e-05, "loss": 0.6494, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.451950807259676, "learning_rate": 3.958691832005981e-05, "loss": 0.6705, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5777524610450411, "learning_rate": 3.9575405199267944e-05, "loss": 0.6172, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.7348686259557948, "learning_rate": 3.956373555405774e-05, "loss": 0.6379, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.631352263160398, "learning_rate": 3.955190947773937e-05, "loss": 0.6138, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.5606800403771885, "learning_rate": 3.9539927064873824e-05, "loss": 0.6533, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.463413991711404, "learning_rate": 3.952778841127214e-05, "loss": 0.6402, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5016958107479539, "learning_rate": 3.95154936139947e-05, "loss": 0.6264, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.6322684155956941, "learning_rate": 3.950304277135034e-05, "loss": 0.6494, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.5650678861745151, "learning_rate": 3.94904359828957e-05, "loss": 0.6216, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.6011779904926358, "learning_rate": 3.94776733494343e-05, "loss": 0.6118, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.5297492148735644, "learning_rate": 3.9464754973015826e-05, "loss": 0.6252, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5634724326631957, "learning_rate": 3.9451680956935275e-05, "loss": 0.637, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.7625997328353205, "learning_rate": 3.943845140573213e-05, "loss": 0.6212, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.5602762347390207, "learning_rate": 3.942506642518952e-05, "loss": 0.6219, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.5230094706819621, "learning_rate": 3.9411526122333396e-05, "loss": 0.6362, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.44530111038850045, "learning_rate": 3.939783060543167e-05, "loss": 0.6292, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5210368185979716, "learning_rate": 3.938397998399333e-05, "loss": 0.6306, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.5241649679288084, "learning_rate": 3.936997436876756e-05, "loss": 0.6496, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.44653396154016756, "learning_rate": 3.935581387174289e-05, "loss": 0.6203, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5637467391742284, "learning_rate": 3.9341498606146295e-05, "loss": 0.6286, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.5594663638742563, "learning_rate": 3.932702868644224e-05, "loss": 0.64, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.636695129535303, "learning_rate": 3.931240422833181e-05, "loss": 0.6364, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.697860762861098, "learning_rate": 3.9297625348751806e-05, "loss": 0.6326, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.9144780153548218, "learning_rate": 3.9282692165873744e-05, "loss": 0.6233, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.7955919770480387, "learning_rate": 3.9267604799102945e-05, "loss": 0.6203, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.43907855848545657, "learning_rate": 3.9252363369077615e-05, "loss": 0.6253, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.727351517757469, "learning_rate": 3.9236967997667796e-05, "loss": 0.6057, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.6361253799765335, "learning_rate": 3.9221418807974496e-05, "loss": 0.6366, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.44716324653873796, "learning_rate": 3.92057159243286e-05, "loss": 0.6293, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.6813198008315962, "learning_rate": 3.9189859472289956e-05, "loss": 0.6243, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6244236834710108, "learning_rate": 3.9173849578646324e-05, "loss": 0.6262, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.5226348885472561, "learning_rate": 3.9157686371412395e-05, "loss": 0.6183, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.4752611289171076, "learning_rate": 3.914136997982874e-05, "loss": 0.6377, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.6034188835698424, "learning_rate": 3.912490053436079e-05, "loss": 0.6335, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5262020892560177, "learning_rate": 3.9108278166697805e-05, "loss": 0.6132, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.47644670648136545, "learning_rate": 3.909150300975178e-05, "loss": 0.6251, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4520854416871816, "learning_rate": 3.907457519765642e-05, "loss": 0.6203, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5314004905618378, "learning_rate": 3.905749486576607e-05, "loss": 0.6248, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.47978039143463597, "learning_rate": 3.90402621506546e-05, "loss": 0.6456, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4625686175259827, "learning_rate": 3.902287719011435e-05, "loss": 0.6247, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.4336227866778661, "learning_rate": 3.900534012315499e-05, "loss": 0.6441, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.4363093575945989, "learning_rate": 3.8987651090002454e-05, "loss": 0.6387, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.4474698953963271, "learning_rate": 3.896981023209777e-05, "loss": 0.6236, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4356461219185453, "learning_rate": 3.8951817692095966e-05, "loss": 0.6331, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.39999568644961514, "learning_rate": 3.893367361386491e-05, "loss": 0.6228, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4172900140668212, "learning_rate": 3.891537814248417e-05, "loss": 0.6334, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4521400717671546, "learning_rate": 3.889693142424384e-05, "loss": 0.6184, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.4350052153551877, "learning_rate": 3.8878333606643405e-05, "loss": 0.637, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.41375553775963203, "learning_rate": 3.885958483839049e-05, "loss": 0.6213, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.46085333434784376, "learning_rate": 3.8840685269399786e-05, "loss": 0.6438, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.44556002082010626, "learning_rate": 3.882163505079171e-05, "loss": 0.5928, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.40109389984585486, "learning_rate": 3.880243433489132e-05, "loss": 0.6082, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5993704518950292, "learning_rate": 3.878308327522702e-05, "loss": 0.5554, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.56071757354835, "learning_rate": 3.876358202652936e-05, "loss": 0.5609, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.6545699352882053, "learning_rate": 3.8743930744729835e-05, "loss": 0.5603, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.7499216296372956, "learning_rate": 3.8724129586959535e-05, "loss": 0.5535, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.6605094298653278, "learning_rate": 3.870417871154801e-05, "loss": 0.5526, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.5765623912453399, "learning_rate": 3.868407827802192e-05, "loss": 0.5526, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.612188517805889, "learning_rate": 3.8663828447103804e-05, "loss": 0.5608, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.48405522327939615, "learning_rate": 3.8643429380710765e-05, "loss": 0.5644, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.49080379577560773, "learning_rate": 3.862288124195319e-05, "loss": 0.5345, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.49143616707087334, "learning_rate": 3.8602184195133464e-05, "loss": 0.5566, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5757594111818349, "learning_rate": 3.8581338405744604e-05, "loss": 0.5347, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.5775614254055239, "learning_rate": 3.8560344040468996e-05, "loss": 0.5621, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.45340449447148545, "learning_rate": 3.853920126717703e-05, "loss": 0.5571, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5770466920328332, "learning_rate": 3.851791025492574e-05, "loss": 0.5557, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.4791880728943013, "learning_rate": 3.8496471173957515e-05, "loss": 0.5305, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.4941887655047615, "learning_rate": 3.847488419569866e-05, "loss": 0.5599, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.553973966903351, "learning_rate": 3.8453149492758077e-05, "loss": 0.5702, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.4425650786822152, "learning_rate": 3.8431267238925886e-05, "loss": 0.5531, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.492116047949222, "learning_rate": 3.840923760917199e-05, "loss": 0.5522, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.42839832104575537, "learning_rate": 3.838706077964473e-05, "loss": 0.5405, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.44816478162870504, "learning_rate": 3.836473692766944e-05, "loss": 0.5682, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5480590787992959, "learning_rate": 3.834226623174705e-05, "loss": 0.5293, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.7255575599976749, "learning_rate": 3.831964887155264e-05, "loss": 0.5628, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.5859450655851857, "learning_rate": 3.829688502793403e-05, "loss": 0.5349, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5086921133436889, "learning_rate": 3.827397488291029e-05, "loss": 0.5478, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.5745412793244284, "learning_rate": 3.8250918619670343e-05, "loss": 0.5403, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5994346571350815, "learning_rate": 3.822771642257145e-05, "loss": 0.5632, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5138186157925072, "learning_rate": 3.820436847713776e-05, "loss": 0.5341, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.47354279201552985, "learning_rate": 3.8180874970058826e-05, "loss": 0.5723, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.4690149440400113, "learning_rate": 3.8157236089188103e-05, "loss": 0.5277, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.46771042874708074, "learning_rate": 3.813345202354145e-05, "loss": 0.5559, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.49147865083866205, "learning_rate": 3.810952296329563e-05, "loss": 0.5577, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.6081674404603121, "learning_rate": 3.808544909978676e-05, "loss": 0.5222, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.41485627955549464, "learning_rate": 3.806123062550882e-05, "loss": 0.544, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.5915838804633915, "learning_rate": 3.803686773411208e-05, "loss": 0.5554, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.5752669680983743, "learning_rate": 3.801236062040158e-05, "loss": 0.5631, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.45189155472784664, "learning_rate": 3.798770948033553e-05, "loss": 0.5413, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5109164423468536, "learning_rate": 3.796291451102381e-05, "loss": 0.5456, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.45745820192369463, "learning_rate": 3.793797591072631e-05, "loss": 0.5398, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.5926972135649198, "learning_rate": 3.791289387885144e-05, "loss": 0.5587, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.43665952265813457, "learning_rate": 3.788766861595443e-05, "loss": 0.5599, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5907631098502588, "learning_rate": 3.7862300323735835e-05, "loss": 0.5481, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.4952597298129882, "learning_rate": 3.783678920503983e-05, "loss": 0.5639, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.6846272557765066, "learning_rate": 3.781113546385265e-05, "loss": 0.5429, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.6042682902926977, "learning_rate": 3.7785339305300916e-05, "loss": 0.5655, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5076737708485649, "learning_rate": 3.7759400935650025e-05, "loss": 0.5443, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.4752212312253001, "learning_rate": 3.77333205623025e-05, "loss": 0.5621, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.4865109722989083, "learning_rate": 3.7707098393796295e-05, "loss": 0.5491, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.4556132499862622, "learning_rate": 3.7680734639803185e-05, "loss": 0.5425, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.4054625035621103, "learning_rate": 3.765422951112704e-05, "loss": 0.5482, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.4421562087318841, "learning_rate": 3.762758321970216e-05, "loss": 0.5476, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.45123416611341244, "learning_rate": 3.7600795978591584e-05, "loss": 0.5507, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.542430516265146, "learning_rate": 3.757386800198538e-05, "loss": 0.5642, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.744758316268878, "learning_rate": 3.7546799505198925e-05, "loss": 0.5632, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5006473766005901, "learning_rate": 3.7519590704671197e-05, "loss": 0.5577, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5262974162525017, "learning_rate": 3.749224181796305e-05, "loss": 0.5636, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5455326671870923, "learning_rate": 3.746475306375545e-05, "loss": 0.5387, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.42830919142563234, "learning_rate": 3.743712466184774e-05, "loss": 0.5565, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.49309295042492546, "learning_rate": 3.7409356833155885e-05, "loss": 0.5498, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4409986898899442, "learning_rate": 3.73814497997107e-05, "loss": 0.5659, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.49815271361698255, "learning_rate": 3.7353403784656095e-05, "loss": 0.5369, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.3968935282483149, "learning_rate": 3.732521901224724e-05, "loss": 0.5548, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.4120047263624668, "learning_rate": 3.7296895707848844e-05, "loss": 0.5409, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.44532933712162376, "learning_rate": 3.7268434097933275e-05, "loss": 0.5561, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.4569633055465456, "learning_rate": 3.723983441007882e-05, "loss": 0.5383, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.436217241244805, "learning_rate": 3.721109687296781e-05, "loss": 0.5441, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.47775209386114276, "learning_rate": 3.718222171638484e-05, "loss": 0.5552, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.4391229850912191, "learning_rate": 3.715320917121488e-05, "loss": 0.5676, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.421394542090377, "learning_rate": 3.712405946944149e-05, "loss": 0.5558, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.43217296845211733, "learning_rate": 3.709477284414488e-05, "loss": 0.5441, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.41181464676513463, "learning_rate": 3.7065349529500136e-05, "loss": 0.5473, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.43754407012389857, "learning_rate": 3.7035789760775305e-05, "loss": 0.546, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.45682440038376304, "learning_rate": 3.70060937743295e-05, "loss": 0.5514, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.45770978018551967, "learning_rate": 3.6976261807611045e-05, "loss": 0.5437, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.5030634407999999, "learning_rate": 3.694629409915555e-05, "loss": 0.5455, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6029115153575334, "learning_rate": 3.691619088858401e-05, "loss": 0.5593, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.4515765906287395, "learning_rate": 3.68859524166009e-05, "loss": 0.5699, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.3969604904115277, "learning_rate": 3.6855578924992226e-05, "loss": 0.5412, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.43864701307563586, "learning_rate": 3.6825070656623626e-05, "loss": 0.5554, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.39746525873177135, "learning_rate": 3.67944278554384e-05, "loss": 0.5639, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.39291517688254063, "learning_rate": 3.676365076645557e-05, "loss": 0.5328, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4202242776486969, "learning_rate": 3.673273963576791e-05, "loss": 0.5418, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.441737764573713, "learning_rate": 3.670169471054001e-05, "loss": 0.5403, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.39902703743432016, "learning_rate": 3.6670516239006254e-05, "loss": 0.5515, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.46522088322768673, "learning_rate": 3.663920447046888e-05, "loss": 0.5511, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.48381117129146856, "learning_rate": 3.6607759655295954e-05, "loss": 0.5577, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.4378987973761009, "learning_rate": 3.657618204491937e-05, "loss": 0.5348, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.44721351364459205, "learning_rate": 3.6544471891832875e-05, "loss": 0.5527, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4755129457302031, "learning_rate": 3.6512629449589983e-05, "loss": 0.5606, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.5453221592999926, "learning_rate": 3.6480654972802045e-05, "loss": 0.5589, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5192625192624354, "learning_rate": 3.644854871713611e-05, "loss": 0.5602, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.4655207148912435, "learning_rate": 3.6416310939312924e-05, "loss": 0.5335, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.4502062491833012, "learning_rate": 3.638394189710493e-05, "loss": 0.5465, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.4621328967270458, "learning_rate": 3.635144184933412e-05, "loss": 0.5461, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.6064346562162592, "learning_rate": 3.6318811055869994e-05, "loss": 0.564, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.45531923958696563, "learning_rate": 3.628604977762752e-05, "loss": 0.5661, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.49130178022286275, "learning_rate": 3.6253158276565004e-05, "loss": 0.5506, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.6172735846036737, "learning_rate": 3.6220136815682016e-05, "loss": 0.5499, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.4784431504845715, "learning_rate": 3.618698565901727e-05, "loss": 0.5682, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.5232030379729419, "learning_rate": 3.615370507164654e-05, "loss": 0.5709, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.6015795761521149, "learning_rate": 3.61202953196805e-05, "loss": 0.5636, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5855278528515356, "learning_rate": 3.6086756670262654e-05, "loss": 0.5401, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.40335483879112527, "learning_rate": 3.6053089391567135e-05, "loss": 0.5524, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.6033581041445758, "learning_rate": 3.601929375279662e-05, "loss": 0.5739, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.5631237725890398, "learning_rate": 3.598537002418012e-05, "loss": 0.5732, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.5524792977792079, "learning_rate": 3.5951318476970885e-05, "loss": 0.5527, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.539945973891763, "learning_rate": 3.591713938344416e-05, "loss": 0.5553, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.6156513461226794, "learning_rate": 3.588283301689507e-05, "loss": 0.5364, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.5130619669924061, "learning_rate": 3.5848399651636424e-05, "loss": 0.5642, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.5681789630933417, "learning_rate": 3.5813839562996473e-05, "loss": 0.5458, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5642727980310833, "learning_rate": 3.5779153027316775e-05, "loss": 0.5617, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.5809024319560816, "learning_rate": 3.574434032194994e-05, "loss": 0.5411, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.6310488196685812, "learning_rate": 3.5709401725257436e-05, "loss": 0.5635, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.5848171505801706, "learning_rate": 3.5674337516607346e-05, "loss": 0.5474, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.6265326138778173, "learning_rate": 3.563914797637216e-05, "loss": 0.5386, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5679079084137102, "learning_rate": 3.560383338592649e-05, "loss": 0.5447, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5249517523547614, "learning_rate": 3.556839402764487e-05, "loss": 0.5352, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.6265179508159465, "learning_rate": 3.553283018489946e-05, "loss": 0.5541, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.49720856632170185, "learning_rate": 3.54971421420578e-05, "loss": 0.5618, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5041140195430817, "learning_rate": 3.5461330184480524e-05, "loss": 0.5346, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.5454497675977573, "learning_rate": 3.54253945985191e-05, "loss": 0.5317, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4069991438807485, "learning_rate": 3.5389335671513524e-05, "loss": 0.5388, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.4927130661925273, "learning_rate": 3.5353153691789986e-05, "loss": 0.5447, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.4978380504557083, "learning_rate": 3.531684894865866e-05, "loss": 0.5408, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4216686935432293, "learning_rate": 3.528042173241128e-05, "loss": 0.5486, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4043543009264407, "learning_rate": 3.524387233431892e-05, "loss": 0.5556, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.6034469450217138, "learning_rate": 3.520720104662958e-05, "loss": 0.5567, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.7061263050903435, "learning_rate": 3.5170408162565904e-05, "loss": 0.5403, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.41585144835608245, "learning_rate": 3.513349397632281e-05, "loss": 0.5487, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.7216737817810969, "learning_rate": 3.5096458783065145e-05, "loss": 0.5472, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.7661578970941757, "learning_rate": 3.505930287892533e-05, "loss": 0.565, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.44927383952158145, "learning_rate": 3.502202656100099e-05, "loss": 0.5374, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.46329952699504096, "learning_rate": 3.498463012735256e-05, "loss": 0.5429, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.5466223878654469, "learning_rate": 3.494711387700094e-05, "loss": 0.5529, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.4070051534973491, "learning_rate": 3.490947810992505e-05, "loss": 0.5454, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.4701545000261539, "learning_rate": 3.48717231270595e-05, "loss": 0.56, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.5567615580378803, "learning_rate": 3.483384923029211e-05, "loss": 0.5457, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.3908760393554781, "learning_rate": 3.479585672246156e-05, "loss": 0.5542, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.4679611620338219, "learning_rate": 3.4757745907354924e-05, "loss": 0.5465, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4046889183675197, "learning_rate": 3.471951708970527e-05, "loss": 0.5403, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.437077095048839, "learning_rate": 3.468117057518921e-05, "loss": 0.5654, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.4161282442539873, "learning_rate": 3.4642706670424426e-05, "loss": 0.5555, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.3975270135544584, "learning_rate": 3.460412568296731e-05, "loss": 0.5484, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.38437660678575725, "learning_rate": 3.456542792131039e-05, "loss": 0.5515, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.384017745651129, "learning_rate": 3.4526613694879936e-05, "loss": 0.5562, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.39697306429448814, "learning_rate": 3.448768331403348e-05, "loss": 0.5624, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.42460410363362017, "learning_rate": 3.44486370900573e-05, "loss": 0.5594, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.39093656866066817, "learning_rate": 3.440947533516396e-05, "loss": 0.5731, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.4813368233775931, "learning_rate": 3.4370198362489816e-05, "loss": 0.5582, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.38406084355593867, "learning_rate": 3.43308064860925e-05, "loss": 0.5415, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.45747185520877964, "learning_rate": 3.4291300020948393e-05, "loss": 0.5418, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.44066954498466426, "learning_rate": 3.425167928295015e-05, "loss": 0.5692, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.4062813907507556, "learning_rate": 3.421194458890411e-05, "loss": 0.5538, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.4297309508308357, "learning_rate": 3.4172096256527865e-05, "loss": 0.5406, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.4043465799099397, "learning_rate": 3.4132134604447595e-05, "loss": 0.5445, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.3840437911280598, "learning_rate": 3.409205995219561e-05, "loss": 0.547, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.40719626164292766, "learning_rate": 3.4051872620207765e-05, "loss": 0.5283, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.3921364398705629, "learning_rate": 3.40115729298209e-05, "loss": 0.5684, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.3803054770437065, "learning_rate": 3.397116120327025e-05, "loss": 0.5438, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.38089565093709576, "learning_rate": 3.3930637763686916e-05, "loss": 0.5589, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.44756869360163426, "learning_rate": 3.389000293509524e-05, "loss": 0.5362, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.3662295611051611, "learning_rate": 3.3849257042410225e-05, "loss": 0.5718, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.4948204139011226, "learning_rate": 3.380840041143494e-05, "loss": 0.5564, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.43901365008236065, "learning_rate": 3.376743336885792e-05, "loss": 0.542, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.36665434026924787, "learning_rate": 3.372635624225055e-05, "loss": 0.5527, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.38763791016047483, "learning_rate": 3.3685169360064445e-05, "loss": 0.546, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4454818659954635, "learning_rate": 3.3643873051628804e-05, "loss": 0.553, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.34248162571172897, "learning_rate": 3.3602467647147814e-05, "loss": 0.5448, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.4034443907044299, "learning_rate": 3.356095347769799e-05, "loss": 0.5495, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.40522020953539367, "learning_rate": 3.351933087522552e-05, "loss": 0.547, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.3473908799753145, "learning_rate": 3.3477600172543626e-05, "loss": 0.5547, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.4105448121729926, "learning_rate": 3.3435761703329894e-05, "loss": 0.5423, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.42855125511265874, "learning_rate": 3.3393815802123606e-05, "loss": 0.5551, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.4223982403908447, "learning_rate": 3.335176280432308e-05, "loss": 0.5203, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.5617059677966455, "learning_rate": 3.330960304618295e-05, "loss": 0.551, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.39828198218364885, "learning_rate": 3.326733686481153e-05, "loss": 0.5446, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.5859592040276653, "learning_rate": 3.3224964598168084e-05, "loss": 0.5548, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.5809219512849042, "learning_rate": 3.318248658506012e-05, "loss": 0.5796, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.34362074779336355, "learning_rate": 3.313990316514069e-05, "loss": 0.544, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.5195436174162251, "learning_rate": 3.309721467890571e-05, "loss": 0.5513, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.45013814139111835, "learning_rate": 3.305442146769115e-05, "loss": 0.5528, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.4030907856638431, "learning_rate": 3.30115238736704e-05, "loss": 0.5584, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.42767707795482146, "learning_rate": 3.296852223985148e-05, "loss": 0.5505, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3388389627861294, "learning_rate": 3.2925416910074315e-05, "loss": 0.5545, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.47989245219584303, "learning_rate": 3.288220822900796e-05, "loss": 0.5345, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.38350918462754335, "learning_rate": 3.283889654214788e-05, "loss": 0.5626, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.4068393099392754, "learning_rate": 3.279548219581317e-05, "loss": 0.5451, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.43993483672282385, "learning_rate": 3.275196553714379e-05, "loss": 0.547, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.3805490462159161, "learning_rate": 3.270834691409778e-05, "loss": 0.5413, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.42052317685821056, "learning_rate": 3.266462667544849e-05, "loss": 0.5431, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.40427157465373936, "learning_rate": 3.262080517078178e-05, "loss": 0.5484, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.3870135035017012, "learning_rate": 3.257688275049323e-05, "loss": 0.5618, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.5050637286688873, "learning_rate": 3.253285976578535e-05, "loss": 0.5369, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.5123884144609384, "learning_rate": 3.2488736568664756e-05, "loss": 0.5421, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.37583582006886984, "learning_rate": 3.244451351193935e-05, "loss": 0.5524, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.6145372638124895, "learning_rate": 3.240019094921551e-05, "loss": 0.5318, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.38148914556641167, "learning_rate": 3.235576923489527e-05, "loss": 0.5435, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.5681273639259238, "learning_rate": 3.2311248724173476e-05, "loss": 0.5553, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.38197060383918274, "learning_rate": 3.226662977303494e-05, "loss": 0.5452, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4954843410529809, "learning_rate": 3.2221912738251626e-05, "loss": 0.5559, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.38787169190662446, "learning_rate": 3.2177097977379736e-05, "loss": 0.5625, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.47110597161013473, "learning_rate": 3.21321858487569e-05, "loss": 0.5508, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.43066089601074686, "learning_rate": 3.208717671149931e-05, "loss": 0.5544, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4139703105010596, "learning_rate": 3.204207092549882e-05, "loss": 0.551, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.4098542295951356, "learning_rate": 3.19968688514201e-05, "loss": 0.5633, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.38330972846058214, "learning_rate": 3.195157085069774e-05, "loss": 0.5646, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.46141470993863554, "learning_rate": 3.190617728553332e-05, "loss": 0.5576, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.37458593223170333, "learning_rate": 3.1860688518892606e-05, "loss": 0.5415, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.5202494977717991, "learning_rate": 3.181510491450254e-05, "loss": 0.5599, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.355071792484685, "learning_rate": 3.176942683684842e-05, "loss": 0.5579, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.5603876760876303, "learning_rate": 3.1723654651170934e-05, "loss": 0.5678, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.44997023831880417, "learning_rate": 3.167778872346327e-05, "loss": 0.5517, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.3851476546238971, "learning_rate": 3.163182942046815e-05, "loss": 0.5432, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.42732485055301633, "learning_rate": 3.158577710967494e-05, "loss": 0.5735, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.40887947112060785, "learning_rate": 3.153963215931669e-05, "loss": 0.5465, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.3791656936436408, "learning_rate": 3.14933949383672e-05, "loss": 0.5395, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.38417295906903004, "learning_rate": 3.144706581653805e-05, "loss": 0.5522, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.4043138005957414, "learning_rate": 3.140064516427566e-05, "loss": 0.5485, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.4231665896983369, "learning_rate": 3.135413335275833e-05, "loss": 0.543, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.3395962565114176, "learning_rate": 3.130753075389327e-05, "loss": 0.5437, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4040591289791215, "learning_rate": 3.1260837740313625e-05, "loss": 0.5308, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.33648051059743855, "learning_rate": 3.121405468537547e-05, "loss": 0.5509, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.43093434182558193, "learning_rate": 3.116718196315488e-05, "loss": 0.5347, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.39498570258298565, "learning_rate": 3.1120219948444894e-05, "loss": 0.5441, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.3905884863594222, "learning_rate": 3.107316901675252e-05, "loss": 0.5631, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.3716674170416754, "learning_rate": 3.1026029544295745e-05, "loss": 0.5469, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.3799674452165155, "learning_rate": 3.097880190800057e-05, "loss": 0.552, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.39027231730611656, "learning_rate": 3.093148648549788e-05, "loss": 0.5491, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.3405294928308349, "learning_rate": 3.088408365512055e-05, "loss": 0.5339, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.394147142775886, "learning_rate": 3.083659379590034e-05, "loss": 0.5412, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.35039307588906793, "learning_rate": 3.0789017287564913e-05, "loss": 0.5477, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.41604018983124186, "learning_rate": 3.074135451053475e-05, "loss": 0.5435, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3448935013706452, "learning_rate": 3.069360584592015e-05, "loss": 0.5568, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.42677878902422633, "learning_rate": 3.064577167551816e-05, "loss": 0.5449, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.33513017570971304, "learning_rate": 3.059785238180953e-05, "loss": 0.5337, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.4579133376240212, "learning_rate": 3.054984834795566e-05, "loss": 0.5451, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.41271023471626395, "learning_rate": 3.0501759957795537e-05, "loss": 0.5448, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.4164968755043882, "learning_rate": 3.0453587595842627e-05, "loss": 0.5321, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.5011109826047178, "learning_rate": 3.0405331647281856e-05, "loss": 0.5603, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.42598088394231254, "learning_rate": 3.0356992497966508e-05, "loss": 0.5381, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3603138077355529, "learning_rate": 3.0308570534415137e-05, "loss": 0.545, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.42426817763325, "learning_rate": 3.0260066143808467e-05, "loss": 0.5466, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.39458804625276683, "learning_rate": 3.021147971398632e-05, "loss": 0.5556, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.35933883742904094, "learning_rate": 3.0162811633444478e-05, "loss": 0.5399, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.3959763332043832, "learning_rate": 3.0114062291331635e-05, "loss": 0.5504, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.3868873746620454, "learning_rate": 3.0065232077446217e-05, "loss": 0.5707, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.43236895633809513, "learning_rate": 3.001632138223332e-05, "loss": 0.5534, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.682100734043554, "learning_rate": 2.9967330596781565e-05, "loss": 0.4528, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.7514425810975182, "learning_rate": 2.9918260112819952e-05, "loss": 0.4395, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5319922990809036, "learning_rate": 2.9869110322714778e-05, "loss": 0.4242, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5374285932512353, "learning_rate": 2.9819881619466447e-05, "loss": 0.4477, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.451660334695202, "learning_rate": 2.9770574396706364e-05, "loss": 0.4573, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.4052467466303781, "learning_rate": 2.972118904869376e-05, "loss": 0.4378, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4055226539604809, "learning_rate": 2.9671725970312563e-05, "loss": 0.4315, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.4054022045418586, "learning_rate": 2.9622185557068238e-05, "loss": 0.4339, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.4289607101601332, "learning_rate": 2.95725682050846e-05, "loss": 0.4396, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.3891001771478696, "learning_rate": 2.9522874311100684e-05, "loss": 0.4525, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.38302695455214447, "learning_rate": 2.9473104272467526e-05, "loss": 0.4262, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4004726570846191, "learning_rate": 2.942325848714505e-05, "loss": 0.4371, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.36541744721942937, "learning_rate": 2.9373337353698804e-05, "loss": 0.4213, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.39478610543251635, "learning_rate": 2.932334127129686e-05, "loss": 0.429, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.4073717876063569, "learning_rate": 2.9273270639706547e-05, "loss": 0.4356, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.4122588588235133, "learning_rate": 2.922312585929131e-05, "loss": 0.4365, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.4150323084425114, "learning_rate": 2.9172907331007478e-05, "loss": 0.431, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.36844483662908534, "learning_rate": 2.9122615456401053e-05, "loss": 0.4297, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.4328485531152273, "learning_rate": 2.9072250637604535e-05, "loss": 0.4374, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.38432197382958977, "learning_rate": 2.9021813277333667e-05, "loss": 0.4355, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.3869628701836529, "learning_rate": 2.8971303778884244e-05, "loss": 0.4292, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.33918553956846514, "learning_rate": 2.8920722546128863e-05, "loss": 0.4384, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.4410630366214504, "learning_rate": 2.887006998351372e-05, "loss": 0.4315, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3492439653634953, "learning_rate": 2.881934649605535e-05, "loss": 0.4261, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.3895684435928446, "learning_rate": 2.8768552489337408e-05, "loss": 0.4359, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.3404637889127221, "learning_rate": 2.8717688369507425e-05, "loss": 0.4461, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.3585253511711723, "learning_rate": 2.8666754543273535e-05, "loss": 0.4295, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4140459548539462, "learning_rate": 2.8615751417901273e-05, "loss": 0.453, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3546034424300311, "learning_rate": 2.856467940121025e-05, "loss": 0.4568, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.3693156265164546, "learning_rate": 2.8513538901570964e-05, "loss": 0.4464, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.378073930552371, "learning_rate": 2.846233032790149e-05, "loss": 0.4475, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.3685502975895411, "learning_rate": 2.84110540896642e-05, "loss": 0.4554, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.38985464658422303, "learning_rate": 2.8359710596862555e-05, "loss": 0.4344, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.3612076490767478, "learning_rate": 2.8308300260037734e-05, "loss": 0.4364, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3857408824734014, "learning_rate": 2.8256823490265424e-05, "loss": 0.4443, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3605944420098706, "learning_rate": 2.8205280699152515e-05, "loss": 0.4379, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.39314103150129975, "learning_rate": 2.8153672298833777e-05, "loss": 0.4476, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.36540930439736197, "learning_rate": 2.8101998701968615e-05, "loss": 0.439, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.4073469601501673, "learning_rate": 2.805026032173773e-05, "loss": 0.4532, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.38530225503721766, "learning_rate": 2.7998457571839832e-05, "loss": 0.4407, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.3750810444209502, "learning_rate": 2.7946590866488322e-05, "loss": 0.441, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.3751861239384817, "learning_rate": 2.7894660620408e-05, "loss": 0.4426, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.4114401851181899, "learning_rate": 2.784266724883173e-05, "loss": 0.4372, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.34897372449872227, "learning_rate": 2.7790611167497128e-05, "loss": 0.4316, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.36561071245174676, "learning_rate": 2.7738492792643224e-05, "loss": 0.4286, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3546605067032805, "learning_rate": 2.768631254100716e-05, "loss": 0.448, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3469904218601728, "learning_rate": 2.7634070829820836e-05, "loss": 0.4448, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.39580766919456667, "learning_rate": 2.7581768076807592e-05, "loss": 0.4397, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.3696661823775224, "learning_rate": 2.7529404700178832e-05, "loss": 0.4341, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3978715758678523, "learning_rate": 2.7476981118630735e-05, "loss": 0.4543, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.3395100611963215, "learning_rate": 2.742449775134085e-05, "loss": 0.4469, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.4058121451516645, "learning_rate": 2.7371955017964788e-05, "loss": 0.4547, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.3546236427684581, "learning_rate": 2.7319353338632845e-05, "loss": 0.4342, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.34937812547340863, "learning_rate": 2.7266693133946645e-05, "loss": 0.4458, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.39028306609315927, "learning_rate": 2.7213974824975785e-05, "loss": 0.4425, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3452003154446627, "learning_rate": 2.7161198833254464e-05, "loss": 0.4381, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3795920870369003, "learning_rate": 2.7108365580778095e-05, "loss": 0.449, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.33237442060589756, "learning_rate": 2.705547548999996e-05, "loss": 0.452, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.3318668960805207, "learning_rate": 2.7002528983827817e-05, "loss": 0.4379, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3422329129388063, "learning_rate": 2.6949526485620517e-05, "loss": 0.4492, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.350912973304227, "learning_rate": 2.6896468419184623e-05, "loss": 0.4348, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.4179154190178789, "learning_rate": 2.6843355208771024e-05, "loss": 0.4602, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.32578801015656095, "learning_rate": 2.6790187279071536e-05, "loss": 0.4391, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4319432458143363, "learning_rate": 2.67369650552155e-05, "loss": 0.4457, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.37325292623331935, "learning_rate": 2.6683688962766407e-05, "loss": 0.4289, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.3913870794836992, "learning_rate": 2.6630359427718468e-05, "loss": 0.4521, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3787543918293465, "learning_rate": 2.6576976876493225e-05, "loss": 0.4369, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3964978086604979, "learning_rate": 2.652354173593614e-05, "loss": 0.4413, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.3862591167090158, "learning_rate": 2.647005443331317e-05, "loss": 0.4463, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.38698412353493433, "learning_rate": 2.6416515396307354e-05, "loss": 0.4434, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.44186290531247513, "learning_rate": 2.636292505301542e-05, "loss": 0.4554, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3531918352099695, "learning_rate": 2.630928383194431e-05, "loss": 0.4363, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.38654109695469363, "learning_rate": 2.625559216200781e-05, "loss": 0.4575, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.4148023542726198, "learning_rate": 2.620185047252308e-05, "loss": 0.4267, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.35546028516101114, "learning_rate": 2.614805919320723e-05, "loss": 0.4472, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.40570855953843094, "learning_rate": 2.6094218754173895e-05, "loss": 0.4395, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3781288849927121, "learning_rate": 2.60403295859298e-05, "loss": 0.4399, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.38354703476526425, "learning_rate": 2.5986392119371297e-05, "loss": 0.4362, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.3546102966184257, "learning_rate": 2.5932406785780928e-05, "loss": 0.4307, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3696948345238572, "learning_rate": 2.5878374016823987e-05, "loss": 0.4479, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.35086520233864293, "learning_rate": 2.5824294244545045e-05, "loss": 0.4338, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.3364468019463959, "learning_rate": 2.577016790136453e-05, "loss": 0.4533, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3607274394936525, "learning_rate": 2.5715995420075225e-05, "loss": 0.4616, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.32390675437516936, "learning_rate": 2.5661777233838864e-05, "loss": 0.4391, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3260759502239523, "learning_rate": 2.5607513776182616e-05, "loss": 0.4339, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.32768919828601756, "learning_rate": 2.5553205480995633e-05, "loss": 0.4371, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.3298678642286644, "learning_rate": 2.5498852782525604e-05, "loss": 0.4476, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.31363851739067955, "learning_rate": 2.5444456115375252e-05, "loss": 0.4309, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3623441817403507, "learning_rate": 2.539001591449889e-05, "loss": 0.4258, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.35303349694221947, "learning_rate": 2.53355326151989e-05, "loss": 0.4474, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3212448037489511, "learning_rate": 2.5281006653122288e-05, "loss": 0.4437, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3919090260945812, "learning_rate": 2.5226438464257217e-05, "loss": 0.4478, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3455079815595542, "learning_rate": 2.5171828484929447e-05, "loss": 0.4429, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3703454826321609, "learning_rate": 2.5117177151798934e-05, "loss": 0.4405, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.3668645125692482, "learning_rate": 2.506248490185627e-05, "loss": 0.4554, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.30017553927210283, "learning_rate": 2.500775217241923e-05, "loss": 0.4471, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.357669893244122, "learning_rate": 2.4952979401129266e-05, "loss": 0.4511, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3404713274565305, "learning_rate": 2.4898167025948e-05, "loss": 0.4284, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.34074448279495434, "learning_rate": 2.4843315485153703e-05, "loss": 0.4479, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.3895779724897199, "learning_rate": 2.4788425217337856e-05, "loss": 0.43, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.3814564708193343, "learning_rate": 2.4733496661401572e-05, "loss": 0.4269, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.3537998209016552, "learning_rate": 2.4678530256552114e-05, "loss": 0.4531, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.37366695498258135, "learning_rate": 2.46235264422994e-05, "loss": 0.4583, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.30692953379150667, "learning_rate": 2.4568485658452452e-05, "loss": 0.4528, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.4261843967263578, "learning_rate": 2.451340834511592e-05, "loss": 0.4467, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.3313353414130678, "learning_rate": 2.4458294942686528e-05, "loss": 0.4504, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.3373003324159667, "learning_rate": 2.440314589184958e-05, "loss": 0.4219, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.35145611059823784, "learning_rate": 2.434796163357541e-05, "loss": 0.4366, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3112751623442512, "learning_rate": 2.429274260911588e-05, "loss": 0.4413, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.3535642704620351, "learning_rate": 2.423748926000084e-05, "loss": 0.4632, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3004638137284161, "learning_rate": 2.418220202803459e-05, "loss": 0.4372, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.327988298275529, "learning_rate": 2.412688135529237e-05, "loss": 0.4563, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.34626747938143604, "learning_rate": 2.4071527684116807e-05, "loss": 0.4405, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.3394640530816509, "learning_rate": 2.4016141457114372e-05, "loss": 0.4529, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.34091145960526503, "learning_rate": 2.396072311715187e-05, "loss": 0.4499, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3429495559557206, "learning_rate": 2.3905273107352863e-05, "loss": 0.44, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.3559021605822097, "learning_rate": 2.3849791871094157e-05, "loss": 0.4508, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.3188240799457985, "learning_rate": 2.379427985200223e-05, "loss": 0.445, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3703274460175199, "learning_rate": 2.373873749394972e-05, "loss": 0.4395, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.3413206590790695, "learning_rate": 2.3683165241051836e-05, "loss": 0.4425, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.32958426309598116, "learning_rate": 2.3627563537662823e-05, "loss": 0.4438, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.36295585664209296, "learning_rate": 2.3571932828372433e-05, "loss": 0.442, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.36321875123609476, "learning_rate": 2.351627355800233e-05, "loss": 0.4464, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.34689050128994353, "learning_rate": 2.346058617160256e-05, "loss": 0.4345, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.33977109317059123, "learning_rate": 2.3404871114447976e-05, "loss": 0.4605, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.34883501696745656, "learning_rate": 2.334912883203469e-05, "loss": 0.4463, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3936312185547429, "learning_rate": 2.3293359770076505e-05, "loss": 0.444, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.3451126480761896, "learning_rate": 2.323756437450136e-05, "loss": 0.4408, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.3370360179147573, "learning_rate": 2.3181743091447754e-05, "loss": 0.4427, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.37461164481146575, "learning_rate": 2.3125896367261164e-05, "loss": 0.441, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.337855477309556, "learning_rate": 2.307002464849052e-05, "loss": 0.4573, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.3803297080930982, "learning_rate": 2.30141283818846e-05, "loss": 0.4386, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3200358296357118, "learning_rate": 2.2958208014388462e-05, "loss": 0.4442, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3520373085263051, "learning_rate": 2.2902263993139857e-05, "loss": 0.4475, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.34820515170255645, "learning_rate": 2.2846296765465708e-05, "loss": 0.4272, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.37740673107643036, "learning_rate": 2.2790306778878465e-05, "loss": 0.4383, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.38371481246964084, "learning_rate": 2.273429448107257e-05, "loss": 0.4377, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.35919027086163274, "learning_rate": 2.2678260319920868e-05, "loss": 0.4336, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.44707117383975664, "learning_rate": 2.262220474347102e-05, "loss": 0.435, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.36678004736790903, "learning_rate": 2.2566128199941918e-05, "loss": 0.4398, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.4161406594972455, "learning_rate": 2.2510031137720104e-05, "loss": 0.4652, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.36337098384307315, "learning_rate": 2.2453914005356206e-05, "loss": 0.4347, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.41305756646800573, "learning_rate": 2.2397777251561302e-05, "loss": 0.4427, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.41417587886593765, "learning_rate": 2.2341621325203393e-05, "loss": 0.459, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3324792462758052, "learning_rate": 2.2285446675303764e-05, "loss": 0.4661, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.38610852320970523, "learning_rate": 2.2229253751033423e-05, "loss": 0.42, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.33370099889518157, "learning_rate": 2.2173043001709492e-05, "loss": 0.4576, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3804939027975418, "learning_rate": 2.2116814876791627e-05, "loss": 0.4463, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.3133674480810606, "learning_rate": 2.2060569825878413e-05, "loss": 0.436, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.3250054111818276, "learning_rate": 2.2004308298703777e-05, "loss": 0.4303, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.31811771204990125, "learning_rate": 2.1948030745133396e-05, "loss": 0.4528, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3760452797340428, "learning_rate": 2.1891737615161083e-05, "loss": 0.4537, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3197253789435013, "learning_rate": 2.1835429358905218e-05, "loss": 0.4522, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3285882514391227, "learning_rate": 2.17791064266051e-05, "loss": 0.4475, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.33718232844014373, "learning_rate": 2.172276926861741e-05, "loss": 0.4642, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.32808764423922165, "learning_rate": 2.166641833541255e-05, "loss": 0.4497, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.373764421100225, "learning_rate": 2.161005407757109e-05, "loss": 0.4461, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.33728558119241503, "learning_rate": 2.155367694578013e-05, "loss": 0.4601, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.35218942847975876, "learning_rate": 2.1497287390829712e-05, "loss": 0.4435, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.31983564641495954, "learning_rate": 2.1440885863609208e-05, "loss": 0.4595, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.3322649881408221, "learning_rate": 2.1384472815103737e-05, "loss": 0.4426, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.31974570452272494, "learning_rate": 2.1328048696390534e-05, "loss": 0.4272, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.3316048866791544, "learning_rate": 2.1271613958635342e-05, "loss": 0.449, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.32250202054387767, "learning_rate": 2.1215169053088825e-05, "loss": 0.4346, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.32268618489067374, "learning_rate": 2.1158714431082937e-05, "loss": 0.4524, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3709357846880329, "learning_rate": 2.110225054402733e-05, "loss": 0.4362, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.3102184002100206, "learning_rate": 2.1045777843405747e-05, "loss": 0.4598, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.34699900425509556, "learning_rate": 2.09892967807724e-05, "loss": 0.439, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3217988944544886, "learning_rate": 2.093280780774835e-05, "loss": 0.4507, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.3250206521022769, "learning_rate": 2.087631137601793e-05, "loss": 0.449, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3014955236167614, "learning_rate": 2.0819807937325104e-05, "loss": 0.4419, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.35184729146075894, "learning_rate": 2.0763297943469847e-05, "loss": 0.4355, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.34973842053602594, "learning_rate": 2.070678184630458e-05, "loss": 0.4449, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.35056270471564166, "learning_rate": 2.06502600977305e-05, "loss": 0.4436, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.33425110327799484, "learning_rate": 2.0593733149694008e-05, "loss": 0.4506, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3279469350525437, "learning_rate": 2.0537201454183074e-05, "loss": 0.4414, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3337765824347056, "learning_rate": 2.0480665463223626e-05, "loss": 0.4535, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3469015851270872, "learning_rate": 2.042412562887594e-05, "loss": 0.4472, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3244217739706194, "learning_rate": 2.0367582403231033e-05, "loss": 0.453, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.34028907912565654, "learning_rate": 2.0311036238407023e-05, "loss": 0.4559, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.3411480665918622, "learning_rate": 2.0254487586545534e-05, "loss": 0.4544, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.30002339302028486, "learning_rate": 2.0197936899808088e-05, "loss": 0.4423, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3090169244468643, "learning_rate": 2.0141384630372466e-05, "loss": 0.4451, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.323599565255254, "learning_rate": 2.0084831230429106e-05, "loss": 0.439, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.30768662269924385, "learning_rate": 2.0028277152177492e-05, "loss": 0.4311, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.32023760969871345, "learning_rate": 1.9971722847822518e-05, "loss": 0.4431, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3328780170089992, "learning_rate": 1.99151687695709e-05, "loss": 0.4526, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.29760848017064295, "learning_rate": 1.9858615369627537e-05, "loss": 0.4515, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.32105988360738696, "learning_rate": 1.9802063100191916e-05, "loss": 0.4574, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.323686427313635, "learning_rate": 1.974551241345447e-05, "loss": 0.4483, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.3206518106239531, "learning_rate": 1.9688963761592984e-05, "loss": 0.4279, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.324954184845426, "learning_rate": 1.963241759676897e-05, "loss": 0.4455, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.30167086392707737, "learning_rate": 1.9575874371124066e-05, "loss": 0.4511, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.3206286958866564, "learning_rate": 1.951933453677638e-05, "loss": 0.4544, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.33883720496557473, "learning_rate": 1.9462798545816932e-05, "loss": 0.4466, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.32796718271124903, "learning_rate": 1.9406266850305996e-05, "loss": 0.4386, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.3043204729317857, "learning_rate": 1.9349739902269503e-05, "loss": 0.438, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3268789039019272, "learning_rate": 1.9293218153695425e-05, "loss": 0.4406, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.33495342054034793, "learning_rate": 1.9236702056530153e-05, "loss": 0.4303, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.2864838028988678, "learning_rate": 1.9180192062674907e-05, "loss": 0.4473, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.32773760068387886, "learning_rate": 1.9123688623982076e-05, "loss": 0.4482, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3460952173838344, "learning_rate": 1.906719219225165e-05, "loss": 0.4397, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.2801882176174057, "learning_rate": 1.9010703219227603e-05, "loss": 0.4379, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.37727534170194044, "learning_rate": 1.8954222156594256e-05, "loss": 0.4396, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.32386911718896105, "learning_rate": 1.8897749455972673e-05, "loss": 0.4464, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.3752556899168505, "learning_rate": 1.884128556891707e-05, "loss": 0.4349, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.3212129016146566, "learning_rate": 1.878483094691119e-05, "loss": 0.4378, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.3535191812243193, "learning_rate": 1.8728386041364664e-05, "loss": 0.4445, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.2942089359158102, "learning_rate": 1.867195130360947e-05, "loss": 0.4315, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.33849579215557324, "learning_rate": 1.8615527184896263e-05, "loss": 0.4443, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.3046530578660286, "learning_rate": 1.8559114136390795e-05, "loss": 0.4502, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.31356313329750596, "learning_rate": 1.8502712609170298e-05, "loss": 0.4313, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.3341839776401729, "learning_rate": 1.8446323054219876e-05, "loss": 0.4455, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.3768523790822561, "learning_rate": 1.838994592242891e-05, "loss": 0.4438, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.3125026966334673, "learning_rate": 1.8333581664587453e-05, "loss": 0.4498, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.34378349873361724, "learning_rate": 1.8277230731382593e-05, "loss": 0.4372, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.30793997346156404, "learning_rate": 1.82208935733949e-05, "loss": 0.4462, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.316786089692968, "learning_rate": 1.8164570641094793e-05, "loss": 0.4492, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.33397142028789595, "learning_rate": 1.810826238483892e-05, "loss": 0.4568, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.34902243683947065, "learning_rate": 1.8051969254866608e-05, "loss": 0.4532, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.3348919686156993, "learning_rate": 1.7995691701296226e-05, "loss": 0.4391, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.3759524463895473, "learning_rate": 1.7939430174121593e-05, "loss": 0.4462, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.34000403993789546, "learning_rate": 1.788318512320838e-05, "loss": 0.4568, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3277473206574305, "learning_rate": 1.782695699829051e-05, "loss": 0.4359, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.32090320562636515, "learning_rate": 1.7770746248966587e-05, "loss": 0.4359, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.305003843502439, "learning_rate": 1.7714553324696243e-05, "loss": 0.4248, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3015928632800456, "learning_rate": 1.7658378674796614e-05, "loss": 0.4357, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.29001585277039604, "learning_rate": 1.76022227484387e-05, "loss": 0.4372, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.31449528378181196, "learning_rate": 1.7546085994643807e-05, "loss": 0.4533, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.30564679142799794, "learning_rate": 1.7489968862279902e-05, "loss": 0.4325, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3284274785499563, "learning_rate": 1.743387180005809e-05, "loss": 0.4495, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.319774402006902, "learning_rate": 1.737779525652899e-05, "loss": 0.4486, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.33591880383576045, "learning_rate": 1.732173968007914e-05, "loss": 0.4308, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.30257542119898595, "learning_rate": 1.7265705518927437e-05, "loss": 0.4357, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.28834025263267804, "learning_rate": 1.7209693221121542e-05, "loss": 0.4301, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.31733132527799096, "learning_rate": 1.7153703234534302e-05, "loss": 0.4417, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.2959303442767598, "learning_rate": 1.709773600686015e-05, "loss": 0.4484, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.3100442260928483, "learning_rate": 1.7041791985611548e-05, "loss": 0.4468, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.3050524511969226, "learning_rate": 1.69858716181154e-05, "loss": 0.4428, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.3560170946985197, "learning_rate": 1.692997535150948e-05, "loss": 0.4414, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.3017373210582244, "learning_rate": 1.687410363273884e-05, "loss": 0.4553, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.31644717825080076, "learning_rate": 1.6818256908552257e-05, "loss": 0.4572, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.29820531747364026, "learning_rate": 1.6762435625498646e-05, "loss": 0.439, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.297045232600005, "learning_rate": 1.67066402299235e-05, "loss": 0.4493, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.30122979739427863, "learning_rate": 1.6650871167965313e-05, "loss": 0.4426, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.3042230063612572, "learning_rate": 1.6595128885552028e-05, "loss": 0.4394, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.2993024756188025, "learning_rate": 1.653941382839745e-05, "loss": 0.4306, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.6683021285640072, "learning_rate": 1.6483726441997673e-05, "loss": 0.3517, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3917050805211257, "learning_rate": 1.642806717162757e-05, "loss": 0.3308, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 1.044447845236989, "learning_rate": 1.637243646233718e-05, "loss": 0.3425, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.5564742594557044, "learning_rate": 1.6316834758948174e-05, "loss": 0.3454, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.5975052304398731, "learning_rate": 1.6261262506050282e-05, "loss": 0.3381, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4176111474013191, "learning_rate": 1.620572014799777e-05, "loss": 0.3388, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.4677403607589582, "learning_rate": 1.6150208128905857e-05, "loss": 0.34, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.4508910487822426, "learning_rate": 1.6094726892647147e-05, "loss": 0.3387, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.45924447873469487, "learning_rate": 1.6039276882848135e-05, "loss": 0.3303, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.43251055369851554, "learning_rate": 1.5983858542885635e-05, "loss": 0.3366, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3776300348844708, "learning_rate": 1.5928472315883203e-05, "loss": 0.3319, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.44451576455076647, "learning_rate": 1.5873118644707633e-05, "loss": 0.3262, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.3728058858936915, "learning_rate": 1.5817797971965413e-05, "loss": 0.3384, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.37634380848826443, "learning_rate": 1.576251073999917e-05, "loss": 0.3248, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.39228591096623744, "learning_rate": 1.5707257390884126e-05, "loss": 0.3325, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.3942683866985262, "learning_rate": 1.5652038366424595e-05, "loss": 0.3437, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3683448455438864, "learning_rate": 1.5596854108150424e-05, "loss": 0.3254, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.34741104370948495, "learning_rate": 1.5541705057313476e-05, "loss": 0.3364, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3931316299135884, "learning_rate": 1.5486591654884086e-05, "loss": 0.3447, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.4017976981613594, "learning_rate": 1.543151434154755e-05, "loss": 0.3367, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.35061063285597316, "learning_rate": 1.5376473557700615e-05, "loss": 0.3362, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3614308546186022, "learning_rate": 1.5321469743447893e-05, "loss": 0.3396, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.3860391537404999, "learning_rate": 1.5266503338598434e-05, "loss": 0.3384, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3337732694646945, "learning_rate": 1.5211574782662149e-05, "loss": 0.3272, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3434081052157031, "learning_rate": 1.5156684514846307e-05, "loss": 0.336, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3535541942809382, "learning_rate": 1.5101832974052012e-05, "loss": 0.332, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3138473137169038, "learning_rate": 1.5047020598870737e-05, "loss": 0.3302, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.35079441043509274, "learning_rate": 1.4992247827580778e-05, "loss": 0.3387, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.2974641402784567, "learning_rate": 1.493751509814374e-05, "loss": 0.3291, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.331295027434099, "learning_rate": 1.4882822848201073e-05, "loss": 0.3212, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.31417726268934665, "learning_rate": 1.4828171515070553e-05, "loss": 0.3306, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.32684525839771195, "learning_rate": 1.4773561535742793e-05, "loss": 0.3125, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.3596253351631177, "learning_rate": 1.4718993346877715e-05, "loss": 0.3411, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.315112576402632, "learning_rate": 1.466446738480111e-05, "loss": 0.3327, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.3637763807235056, "learning_rate": 1.460998408550112e-05, "loss": 0.3311, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3758619277703119, "learning_rate": 1.4555543884624751e-05, "loss": 0.3274, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.37243936851589693, "learning_rate": 1.4501147217474402e-05, "loss": 0.3296, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.40417033578448464, "learning_rate": 1.444679451900437e-05, "loss": 0.3436, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.36047367254600543, "learning_rate": 1.4392486223817397e-05, "loss": 0.324, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3666105911656095, "learning_rate": 1.4338222766161143e-05, "loss": 0.3396, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.375799051473597, "learning_rate": 1.4284004579924777e-05, "loss": 0.3339, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.36273323064180046, "learning_rate": 1.4229832098635479e-05, "loss": 0.333, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.3311371989441796, "learning_rate": 1.4175705755454963e-05, "loss": 0.3408, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.34979430444088716, "learning_rate": 1.412162598317602e-05, "loss": 0.3388, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.30699777041281123, "learning_rate": 1.406759321421907e-05, "loss": 0.3333, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3555320926902616, "learning_rate": 1.401360788062871e-05, "loss": 0.3455, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.32952873241520586, "learning_rate": 1.3959670414070204e-05, "loss": 0.333, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.28483060731664656, "learning_rate": 1.3905781245826108e-05, "loss": 0.3355, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.3326403023402671, "learning_rate": 1.3851940806792778e-05, "loss": 0.3319, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.31688255941901233, "learning_rate": 1.379814952747693e-05, "loss": 0.3423, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2999607355488799, "learning_rate": 1.3744407837992193e-05, "loss": 0.3436, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.34206375993407956, "learning_rate": 1.3690716168055692e-05, "loss": 0.3448, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.30492802331843316, "learning_rate": 1.363707494698459e-05, "loss": 0.3427, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.29179373317761426, "learning_rate": 1.358348460369265e-05, "loss": 0.3324, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.32927138861220356, "learning_rate": 1.352994556668684e-05, "loss": 0.3332, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3061520460909188, "learning_rate": 1.3476458264063865e-05, "loss": 0.3353, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.3077374408458073, "learning_rate": 1.342302312350678e-05, "loss": 0.3297, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3136129869586845, "learning_rate": 1.3369640572281537e-05, "loss": 0.3434, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.31446584246521175, "learning_rate": 1.3316311037233596e-05, "loss": 0.3375, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.32396063096258176, "learning_rate": 1.326303494478451e-05, "loss": 0.342, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3046671634014534, "learning_rate": 1.3209812720928472e-05, "loss": 0.329, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2987936197041793, "learning_rate": 1.315664479122898e-05, "loss": 0.3342, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.31264716392243824, "learning_rate": 1.3103531580815378e-05, "loss": 0.3494, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.3091380933786219, "learning_rate": 1.3050473514379488e-05, "loss": 0.342, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.3105910821715324, "learning_rate": 1.2997471016172188e-05, "loss": 0.3399, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.3027978430449906, "learning_rate": 1.2944524510000042e-05, "loss": 0.3345, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.31137762997637575, "learning_rate": 1.2891634419221908e-05, "loss": 0.3447, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.29725865076078567, "learning_rate": 1.2838801166745545e-05, "loss": 0.3365, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.33041380130727555, "learning_rate": 1.2786025175024216e-05, "loss": 0.3445, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.31966747280586494, "learning_rate": 1.2733306866053357e-05, "loss": 0.3346, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.30497999335789605, "learning_rate": 1.2680646661367163e-05, "loss": 0.3387, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.31858802778938905, "learning_rate": 1.2628044982035219e-05, "loss": 0.333, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.30969689153089053, "learning_rate": 1.2575502248659155e-05, "loss": 0.3282, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.32396138580791817, "learning_rate": 1.2523018881369269e-05, "loss": 0.3485, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2913298552070046, "learning_rate": 1.2470595299821176e-05, "loss": 0.3422, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.3249907983210455, "learning_rate": 1.2418231923192416e-05, "loss": 0.3318, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.31089714385831363, "learning_rate": 1.2365929170179165e-05, "loss": 0.3371, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.29775411798425827, "learning_rate": 1.2313687458992848e-05, "loss": 0.3256, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.30935707211944985, "learning_rate": 1.2261507207356785e-05, "loss": 0.3268, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.3188554180656067, "learning_rate": 1.220938883250288e-05, "loss": 0.324, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2927049869969544, "learning_rate": 1.215733275116827e-05, "loss": 0.3381, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.32705062569253757, "learning_rate": 1.2105339379592005e-05, "loss": 0.3441, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.294277977979379, "learning_rate": 1.2053409133511681e-05, "loss": 0.339, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.29984937470863104, "learning_rate": 1.2001542428160173e-05, "loss": 0.3277, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2957870402355845, "learning_rate": 1.1949739678262278e-05, "loss": 0.3251, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.2895671351739841, "learning_rate": 1.189800129803139e-05, "loss": 0.3291, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3006843419055978, "learning_rate": 1.1846327701166228e-05, "loss": 0.3464, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.3000542321748621, "learning_rate": 1.1794719300847493e-05, "loss": 0.3411, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.28117014092185755, "learning_rate": 1.1743176509734582e-05, "loss": 0.343, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2986573974702844, "learning_rate": 1.1691699739962275e-05, "loss": 0.3303, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.29968783311619995, "learning_rate": 1.1640289403137456e-05, "loss": 0.3385, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.28374970110311953, "learning_rate": 1.1588945910335802e-05, "loss": 0.3327, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.3046437559945525, "learning_rate": 1.1537669672098517e-05, "loss": 0.3301, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.3030188733287111, "learning_rate": 1.1486461098429036e-05, "loss": 0.341, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.29238243949573695, "learning_rate": 1.1435320598789747e-05, "loss": 0.3324, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.3018047234138674, "learning_rate": 1.1384248582098736e-05, "loss": 0.3499, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.31252843477810954, "learning_rate": 1.1333245456726467e-05, "loss": 0.3469, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2917384324798733, "learning_rate": 1.128231163049258e-05, "loss": 0.3386, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.28424392251875163, "learning_rate": 1.123144751066259e-05, "loss": 0.3306, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2914527297197145, "learning_rate": 1.1180653503944657e-05, "loss": 0.3456, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.27925576784347894, "learning_rate": 1.1129930016486287e-05, "loss": 0.3427, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.3218207204752639, "learning_rate": 1.107927745387114e-05, "loss": 0.3411, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.288851694011339, "learning_rate": 1.1028696221115766e-05, "loss": 0.3308, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2949165673638316, "learning_rate": 1.0978186722666341e-05, "loss": 0.3404, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.303317296037196, "learning_rate": 1.0927749362395475e-05, "loss": 0.3307, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.28563463385687743, "learning_rate": 1.0877384543598954e-05, "loss": 0.3299, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.29310337005250353, "learning_rate": 1.0827092668992529e-05, "loss": 0.3433, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2933694501892787, "learning_rate": 1.077687414070869e-05, "loss": 0.3232, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.3009967415762946, "learning_rate": 1.0726729360293451e-05, "loss": 0.3249, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.28025628456551305, "learning_rate": 1.0676658728703147e-05, "loss": 0.3457, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.30821915505792497, "learning_rate": 1.0626662646301198e-05, "loss": 0.3262, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2875055883312426, "learning_rate": 1.0576741512854958e-05, "loss": 0.3317, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.28824226840203093, "learning_rate": 1.052689572753247e-05, "loss": 0.3406, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.29426435219530783, "learning_rate": 1.0477125688899328e-05, "loss": 0.3279, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.27784400920056307, "learning_rate": 1.0427431794915406e-05, "loss": 0.332, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2969711747197294, "learning_rate": 1.0377814442931769e-05, "loss": 0.333, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.29621925843633384, "learning_rate": 1.0328274029687439e-05, "loss": 0.3322, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2825350356985394, "learning_rate": 1.0278810951306253e-05, "loss": 0.3433, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.3047201689772743, "learning_rate": 1.0229425603293647e-05, "loss": 0.3452, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.29682720048467925, "learning_rate": 1.0180118380533558e-05, "loss": 0.3351, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2818626433330617, "learning_rate": 1.0130889677285225e-05, "loss": 0.3412, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.30295983097493157, "learning_rate": 1.008173988718005e-05, "loss": 0.3399, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.27817146056551084, "learning_rate": 1.0032669403218439e-05, "loss": 0.3356, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.30027917655308917, "learning_rate": 9.983678617766677e-06, "loss": 0.3351, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2896261997985908, "learning_rate": 9.934767922553788e-06, "loss": 0.3372, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2919412203150677, "learning_rate": 9.885937708668371e-06, "loss": 0.3302, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.2845969392914679, "learning_rate": 9.837188366555524e-06, "loss": 0.3316, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.3033695977005145, "learning_rate": 9.788520286013691e-06, "loss": 0.3434, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.31907999965938083, "learning_rate": 9.739933856191537e-06, "loss": 0.3329, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.30462201332023203, "learning_rate": 9.691429465584866e-06, "loss": 0.3348, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.2961945324536663, "learning_rate": 9.643007502033492e-06, "loss": 0.3364, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.28602804731866865, "learning_rate": 9.594668352718152e-06, "loss": 0.34, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.28605796017247576, "learning_rate": 9.546412404157383e-06, "loss": 0.3302, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.282699609591158, "learning_rate": 9.498240042204471e-06, "loss": 0.3501, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.2788722725969127, "learning_rate": 9.450151652044339e-06, "loss": 0.3275, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2999194718872204, "learning_rate": 9.402147618190472e-06, "loss": 0.3364, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.30658603985773136, "learning_rate": 9.354228324481841e-06, "loss": 0.3419, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.3004396191008646, "learning_rate": 9.306394154079852e-06, "loss": 0.331, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.29462853268609535, "learning_rate": 9.258645489465254e-06, "loss": 0.3474, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.3053793768245208, "learning_rate": 9.21098271243509e-06, "loss": 0.3296, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.2960755164073938, "learning_rate": 9.163406204099659e-06, "loss": 0.3375, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.31121143519099775, "learning_rate": 9.115916344879452e-06, "loss": 0.3384, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2963857194846661, "learning_rate": 9.068513514502126e-06, "loss": 0.3265, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2910974453118861, "learning_rate": 9.021198091999439e-06, "loss": 0.335, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.2930925681885138, "learning_rate": 8.973970455704251e-06, "loss": 0.3329, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.28840305609788347, "learning_rate": 8.926830983247495e-06, "loss": 0.3264, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.3089151915121815, "learning_rate": 8.879780051555116e-06, "loss": 0.3294, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.29962671930817697, "learning_rate": 8.83281803684512e-06, "loss": 0.3351, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.29111566537957956, "learning_rate": 8.785945314624532e-06, "loss": 0.3366, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.29666042051683006, "learning_rate": 8.739162259686385e-06, "loss": 0.3443, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2830498917508732, "learning_rate": 8.692469246106734e-06, "loss": 0.3411, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.29562950324792137, "learning_rate": 8.645866647241677e-06, "loss": 0.3275, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2868177443205461, "learning_rate": 8.599354835724348e-06, "loss": 0.3329, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2917096291921792, "learning_rate": 8.552934183461958e-06, "loss": 0.3458, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.284531457868258, "learning_rate": 8.506605061632805e-06, "loss": 0.3397, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.2841700072352432, "learning_rate": 8.460367840683308e-06, "loss": 0.3359, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2693555401290969, "learning_rate": 8.414222890325065e-06, "loss": 0.3292, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2802661129074571, "learning_rate": 8.368170579531855e-06, "loss": 0.3212, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.27715236173822816, "learning_rate": 8.322211276536733e-06, "loss": 0.3311, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.279083572317115, "learning_rate": 8.27634534882907e-06, "loss": 0.3423, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.28301583132000385, "learning_rate": 8.230573163151585e-06, "loss": 0.3223, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.28831263970727444, "learning_rate": 8.184895085497466e-06, "loss": 0.3342, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.2825485129066947, "learning_rate": 8.139311481107401e-06, "loss": 0.3338, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.2828463077606529, "learning_rate": 8.093822714466686e-06, "loss": 0.324, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2740141680903244, "learning_rate": 8.048429149302271e-06, "loss": 0.3452, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2836427910950782, "learning_rate": 8.003131148579902e-06, "loss": 0.3447, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2744658635587617, "learning_rate": 7.957929074501182e-06, "loss": 0.3411, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.27436486970725077, "learning_rate": 7.912823288500695e-06, "loss": 0.3284, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.28619895609686835, "learning_rate": 7.867814151243102e-06, "loss": 0.3374, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2785091113404986, "learning_rate": 7.822902022620267e-06, "loss": 0.3376, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.28191956614142644, "learning_rate": 7.778087261748377e-06, "loss": 0.326, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.29907722052707103, "learning_rate": 7.733370226965056e-06, "loss": 0.3379, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2725434011786028, "learning_rate": 7.688751275826527e-06, "loss": 0.3389, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.25902215972165143, "learning_rate": 7.644230765104735e-06, "loss": 0.3268, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.2877120455438745, "learning_rate": 7.599809050784502e-06, "loss": 0.3343, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2794373884613949, "learning_rate": 7.555486488060661e-06, "loss": 0.3243, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.28054315408504776, "learning_rate": 7.511263431335249e-06, "loss": 0.335, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.2594870433368549, "learning_rate": 7.467140234214656e-06, "loss": 0.3315, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.2855123688300235, "learning_rate": 7.423117249506777e-06, "loss": 0.3403, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.2998067729358824, "learning_rate": 7.379194829218231e-06, "loss": 0.3404, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.27565874278719904, "learning_rate": 7.335373324551518e-06, "loss": 0.3369, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.276739956141445, "learning_rate": 7.291653085902224e-06, "loss": 0.3334, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2734366548973821, "learning_rate": 7.248034462856213e-06, "loss": 0.336, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2704401569342686, "learning_rate": 7.20451780418683e-06, "loss": 0.3291, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2950621474227526, "learning_rate": 7.161103457852128e-06, "loss": 0.3378, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.27392935850324357, "learning_rate": 7.117791770992046e-06, "loss": 0.3398, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.27499633892872893, "learning_rate": 7.074583089925688e-06, "loss": 0.3285, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.27536884050144766, "learning_rate": 7.0314777601485155e-06, "loss": 0.3336, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.27820224635141194, "learning_rate": 6.988476126329604e-06, "loss": 0.3263, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.27206220437791234, "learning_rate": 6.945578532308857e-06, "loss": 0.328, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.27195091322903575, "learning_rate": 6.902785321094301e-06, "loss": 0.3304, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.28601757608121775, "learning_rate": 6.8600968348593115e-06, "loss": 0.333, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2652209740805539, "learning_rate": 6.817513414939892e-06, "loss": 0.3453, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.2781803897075331, "learning_rate": 6.775035401831924e-06, "loss": 0.3278, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.26903304229903086, "learning_rate": 6.732663135188473e-06, "loss": 0.3187, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.27358074572509344, "learning_rate": 6.690396953817055e-06, "loss": 0.3482, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.26520500869930935, "learning_rate": 6.648237195676927e-06, "loss": 0.3365, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.2751048176657356, "learning_rate": 6.606184197876395e-06, "loss": 0.3292, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.26850631681813947, "learning_rate": 6.564238296670109e-06, "loss": 0.3374, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.28987053721719275, "learning_rate": 6.52239982745638e-06, "loss": 0.3232, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.27463221610561284, "learning_rate": 6.480669124774484e-06, "loss": 0.3321, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.28130731815462373, "learning_rate": 6.439046522302013e-06, "loss": 0.3409, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.27296365033458003, "learning_rate": 6.397532352852191e-06, "loss": 0.3273, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.2639736871863409, "learning_rate": 6.356126948371202e-06, "loss": 0.3317, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.27003269797083546, "learning_rate": 6.314830639935559e-06, "loss": 0.3193, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.27573513930323096, "learning_rate": 6.273643757749448e-06, "loss": 0.3414, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.276891138099915, "learning_rate": 6.2325666311420856e-06, "loss": 0.3416, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2714765607621841, "learning_rate": 6.1915995885650675e-06, "loss": 0.3346, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.29825460389904773, "learning_rate": 6.150742957589784e-06, "loss": 0.3267, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.275466086294554, "learning_rate": 6.109997064904774e-06, "loss": 0.3393, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.27996503209924334, "learning_rate": 6.069362236313092e-06, "loss": 0.3345, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2840164628930214, "learning_rate": 6.0288387967297565e-06, "loss": 0.325, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.28110084025073473, "learning_rate": 5.988427070179108e-06, "loss": 0.3425, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.29733402005600607, "learning_rate": 5.948127379792234e-06, "loss": 0.3361, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.29050315885498673, "learning_rate": 5.90794004780439e-06, "loss": 0.3335, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.27625617730625945, "learning_rate": 5.867865395552405e-06, "loss": 0.3356, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.2825729218451282, "learning_rate": 5.8279037434721364e-06, "loss": 0.3297, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.2800846557158109, "learning_rate": 5.788055411095892e-06, "loss": 0.3411, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.27489327275479664, "learning_rate": 5.7483207170498625e-06, "loss": 0.3268, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.26895908600045826, "learning_rate": 5.708699979051613e-06, "loss": 0.3291, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.26252766431513397, "learning_rate": 5.66919351390751e-06, "loss": 0.3419, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.27060510997718057, "learning_rate": 5.629801637510188e-06, "loss": 0.3326, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.2747192380298232, "learning_rate": 5.590524664836043e-06, "loss": 0.32, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.2672874770943338, "learning_rate": 5.551362909942708e-06, "loss": 0.3343, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2800546574386651, "learning_rate": 5.51231668596653e-06, "loss": 0.3383, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.28003824167533853, "learning_rate": 5.47338630512007e-06, "loss": 0.3273, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.28445761014430215, "learning_rate": 5.434572078689617e-06, "loss": 0.323, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.26177666185965154, "learning_rate": 5.395874317032694e-06, "loss": 0.3276, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.28162441607898514, "learning_rate": 5.357293329575573e-06, "loss": 0.3333, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2768747937245856, "learning_rate": 5.318829424810797e-06, "loss": 0.3399, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.28312613677193815, "learning_rate": 5.280482910294728e-06, "loss": 0.3274, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.26789845168819115, "learning_rate": 5.242254092645078e-06, "loss": 0.3288, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2770543016995913, "learning_rate": 5.2041432775384445e-06, "loss": 0.334, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.2791464898919409, "learning_rate": 5.166150769707892e-06, "loss": 0.3428, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.2651707463574709, "learning_rate": 5.128276872940503e-06, "loss": 0.3261, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.27244016041440783, "learning_rate": 5.090521890074953e-06, "loss": 0.3329, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2802843497241135, "learning_rate": 5.0528861229990675e-06, "loss": 0.335, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.29069440445016026, "learning_rate": 5.015369872647442e-06, "loss": 0.3245, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2719949113668115, "learning_rate": 4.9779734389990195e-06, "loss": 0.331, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.28572202587351414, "learning_rate": 4.940697121074675e-06, "loss": 0.3447, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.287188559044356, "learning_rate": 4.903541216934864e-06, "loss": 0.3283, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.2758448201366917, "learning_rate": 4.8665060236772e-06, "loss": 0.3343, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.27879984155108295, "learning_rate": 4.829591837434102e-06, "loss": 0.3357, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.28175015709171564, "learning_rate": 4.792798953370424e-06, "loss": 0.3309, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.2645743305844873, "learning_rate": 4.756127665681083e-06, "loss": 0.3318, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.28426184202132043, "learning_rate": 4.719578267588725e-06, "loss": 0.3311, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.27762575719210036, "learning_rate": 4.6831510513413525e-06, "loss": 0.3219, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.5348822696845889, "learning_rate": 4.6468463082100176e-06, "loss": 0.2627, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.39484175286390966, "learning_rate": 4.610664328486485e-06, "loss": 0.2552, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.2931793765519418, "learning_rate": 4.5746054014809e-06, "loss": 0.2581, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.39248572281816363, "learning_rate": 4.5386698155194766e-06, "loss": 0.2698, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.5211890218107789, "learning_rate": 4.502857857942204e-06, "loss": 0.2692, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.4251252978525345, "learning_rate": 4.467169815100549e-06, "loss": 0.2586, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3371557468791631, "learning_rate": 4.431605972355137e-06, "loss": 0.253, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.4302492455434018, "learning_rate": 4.396166614073516e-06, "loss": 0.2683, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.406728737394447, "learning_rate": 4.360852023627846e-06, "loss": 0.2597, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.36391442930390844, "learning_rate": 4.325662483392656e-06, "loss": 0.2601, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.31223630163408, "learning_rate": 4.29059827474257e-06, "loss": 0.2529, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.3161864713937966, "learning_rate": 4.255659678050063e-06, "loss": 0.2654, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.35464654125134654, "learning_rate": 4.22084697268323e-06, "loss": 0.2576, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.3557610673411893, "learning_rate": 4.186160437003535e-06, "loss": 0.2558, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.3403843241935616, "learning_rate": 4.151600348363582e-06, "loss": 0.2617, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.311223764588388, "learning_rate": 4.11716698310493e-06, "loss": 0.282, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.2905889725603653, "learning_rate": 4.082860616555848e-06, "loss": 0.2591, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.3337705260422462, "learning_rate": 4.048681523029125e-06, "loss": 0.2578, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.32193398616973284, "learning_rate": 4.014629975819882e-06, "loss": 0.2658, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.288615023045911, "learning_rate": 3.9807062472033855e-06, "loss": 0.2724, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2930128981904667, "learning_rate": 3.94691060843287e-06, "loss": 0.2528, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.29908609929037777, "learning_rate": 3.913243329737353e-06, "loss": 0.2653, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.29295639649153227, "learning_rate": 3.879704680319503e-06, "loss": 0.2379, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.3265251728042133, "learning_rate": 3.846294928353471e-06, "loss": 0.269, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.2981641925777599, "learning_rate": 3.8130143409827345e-06, "loss": 0.2669, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2792080660034444, "learning_rate": 3.7798631843179887e-06, "loss": 0.2627, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.28903619363797456, "learning_rate": 3.7468417234349973e-06, "loss": 0.2514, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2761667647088246, "learning_rate": 3.7139502223724823e-06, "loss": 0.2641, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2702770797899304, "learning_rate": 3.6811889441300095e-06, "loss": 0.2675, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2835081722590178, "learning_rate": 3.648558150665886e-06, "loss": 0.2737, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.28299624369004683, "learning_rate": 3.616058102895075e-06, "loss": 0.2675, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2780214052064032, "learning_rate": 3.583689060687079e-06, "loss": 0.2688, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.2908846325175621, "learning_rate": 3.5514512828639023e-06, "loss": 0.2685, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.2771756882028618, "learning_rate": 3.51934502719796e-06, "loss": 0.253, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.3143817843059962, "learning_rate": 3.4873705504100185e-06, "loss": 0.2459, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.2766127587404918, "learning_rate": 3.4555281081671345e-06, "loss": 0.2531, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.2927426244626423, "learning_rate": 3.4238179550806326e-06, "loss": 0.2641, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.26789299450786785, "learning_rate": 3.3922403447040497e-06, "loss": 0.2557, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.28620369616877883, "learning_rate": 3.3607955295311247e-06, "loss": 0.2604, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.28378269935911615, "learning_rate": 3.32948376099375e-06, "loss": 0.2693, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.27268652447742664, "learning_rate": 3.2983052894599976e-06, "loss": 0.2565, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2818037776553564, "learning_rate": 3.2672603642320945e-06, "loss": 0.2614, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2738780237130422, "learning_rate": 3.236349233544438e-06, "loss": 0.257, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2567114100235147, "learning_rate": 3.205572144561604e-06, "loss": 0.2651, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2750613446218852, "learning_rate": 3.174929343376374e-06, "loss": 0.2647, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.26993885886318564, "learning_rate": 3.1444210750077777e-06, "loss": 0.26, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2813380302560776, "learning_rate": 3.1140475833991046e-06, "loss": 0.2495, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.2648640155627661, "learning_rate": 3.0838091114159895e-06, "loss": 0.2601, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2974192854701008, "learning_rate": 3.0537059008444524e-06, "loss": 0.2537, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2712543476490332, "learning_rate": 3.0237381923889563e-06, "loss": 0.2642, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.2802890656785191, "learning_rate": 2.9939062256704997e-06, "loss": 0.2548, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.2723290308622574, "learning_rate": 2.964210239224696e-06, "loss": 0.2416, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.27618900222374043, "learning_rate": 2.934650470499869e-06, "loss": 0.2675, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2678613020287592, "learning_rate": 2.905227155855128e-06, "loss": 0.2642, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.28113377182852795, "learning_rate": 2.875940530558519e-06, "loss": 0.2621, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.276160370841917, "learning_rate": 2.8467908287851154e-06, "loss": 0.2618, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.26091163041223703, "learning_rate": 2.8177782836151603e-06, "loss": 0.2641, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2650531301097185, "learning_rate": 2.7889031270321874e-06, "loss": 0.267, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2694152299101328, "learning_rate": 2.760165589921184e-06, "loss": 0.2573, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.27892299390091185, "learning_rate": 2.7315659020667305e-06, "loss": 0.2591, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.24953136326257958, "learning_rate": 2.703104292151164e-06, "loss": 0.2621, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.27720448719255963, "learning_rate": 2.6747809877527607e-06, "loss": 0.2566, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.33026407382968376, "learning_rate": 2.6465962153439082e-06, "loss": 0.2654, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.27436984037884865, "learning_rate": 2.618550200289303e-06, "loss": 0.2616, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2628140522635272, "learning_rate": 2.59064316684412e-06, "loss": 0.258, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.2647009999755025, "learning_rate": 2.562875338152264e-06, "loss": 0.2543, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2791021914268215, "learning_rate": 2.5352469362445552e-06, "loss": 0.2648, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2685552347103452, "learning_rate": 2.5077581820369523e-06, "loss": 0.2564, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.27678609943504545, "learning_rate": 2.480409295328803e-06, "loss": 0.2652, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.2643857326832858, "learning_rate": 2.45320049480108e-06, "loss": 0.2579, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.24715953292381918, "learning_rate": 2.4261319980146293e-06, "loss": 0.2665, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.2621135481002829, "learning_rate": 2.399204021408421e-06, "loss": 0.2657, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.2712142928584343, "learning_rate": 2.3724167802978395e-06, "loss": 0.2617, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.27260877441096193, "learning_rate": 2.3457704888729625e-06, "loss": 0.2602, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.2606051706220438, "learning_rate": 2.3192653601968162e-06, "loss": 0.2552, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.274231609614719, "learning_rate": 2.2929016062037057e-06, "loss": 0.2512, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2608320161630782, "learning_rate": 2.2666794376975055e-06, "loss": 0.2544, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.26879135084930494, "learning_rate": 2.24059906434998e-06, "loss": 0.2656, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.2787567814384264, "learning_rate": 2.214660694699091e-06, "loss": 0.2515, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.2789986536562372, "learning_rate": 2.188864536147355e-06, "loss": 0.2545, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.27590613439486367, "learning_rate": 2.1632107949601757e-06, "loss": 0.269, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.26418422535156216, "learning_rate": 2.137699676264171e-06, "loss": 0.2657, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.2688426370186506, "learning_rate": 2.1123313840455738e-06, "loss": 0.2581, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.2597436379193733, "learning_rate": 2.08710612114857e-06, "loss": 0.2513, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.25920211267680665, "learning_rate": 2.0620240892736953e-06, "loss": 0.2657, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.2600373828345184, "learning_rate": 2.0370854889762e-06, "loss": 0.2509, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.25708488777970523, "learning_rate": 2.0122905196644726e-06, "loss": 0.2651, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.267191686673429, "learning_rate": 1.987639379598427e-06, "loss": 0.2509, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.2572669784470277, "learning_rate": 1.963132265887919e-06, "loss": 0.2696, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.2604846478405084, "learning_rate": 1.9387693744911784e-06, "loss": 0.2589, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.27073190732765257, "learning_rate": 1.9145509002132368e-06, "loss": 0.2549, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.2629265263444265, "learning_rate": 1.8904770367043723e-06, "loss": 0.2477, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.2787483241374799, "learning_rate": 1.8665479764585504e-06, "loss": 0.2665, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.26668764451291355, "learning_rate": 1.8427639108118977e-06, "loss": 0.2486, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2650169533390587, "learning_rate": 1.8191250299411755e-06, "loss": 0.257, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2841691894939852, "learning_rate": 1.7956315228622446e-06, "loss": 0.2588, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2681700291397611, "learning_rate": 1.7722835774285553e-06, "loss": 0.262, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.26670645195472936, "learning_rate": 1.7490813803296624e-06, "loss": 0.268, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.28259603472147493, "learning_rate": 1.726025117089718e-06, "loss": 0.2659, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.263331564515181, "learning_rate": 1.70311497206598e-06, "loss": 0.2546, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.26942582824448413, "learning_rate": 1.6803511284473638e-06, "loss": 0.2521, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.2608624011702334, "learning_rate": 1.6577337682529538e-06, "loss": 0.2519, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.26793365374500605, "learning_rate": 1.6352630723305617e-06, "loss": 0.2705, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2740793789667197, "learning_rate": 1.612939220355272e-06, "loss": 0.2611, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.27064176717809085, "learning_rate": 1.5907623908280112e-06, "loss": 0.2722, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2648299241306475, "learning_rate": 1.568732761074121e-06, "loss": 0.2505, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.27220868462647424, "learning_rate": 1.5468505072419237e-06, "loss": 0.2622, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.2604508779542598, "learning_rate": 1.5251158043013448e-06, "loss": 0.2488, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.26895693231989387, "learning_rate": 1.5035288260424885e-06, "loss": 0.2677, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.27412780592926306, "learning_rate": 1.4820897450742623e-06, "loss": 0.2421, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2679012822513743, "learning_rate": 1.4607987328229767e-06, "loss": 0.2643, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.2645433787993595, "learning_rate": 1.4396559595310056e-06, "loss": 0.2653, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2730117928452795, "learning_rate": 1.4186615942553973e-06, "loss": 0.2565, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2673851751563193, "learning_rate": 1.3978158048665424e-06, "loss": 0.2598, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2706491748290823, "learning_rate": 1.3771187580468115e-06, "loss": 0.2654, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.2623366736397753, "learning_rate": 1.3565706192892392e-06, "loss": 0.2527, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.25672257576161683, "learning_rate": 1.3361715528961993e-06, "loss": 0.257, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.26094487528288857, "learning_rate": 1.3159217219780817e-06, "loss": 0.2612, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.251234986121868, "learning_rate": 1.2958212884519949e-06, "loss": 0.2507, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.2714466362405911, "learning_rate": 1.2758704130404675e-06, "loss": 0.2713, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.2646055618782772, "learning_rate": 1.2560692552701738e-06, "loss": 0.2633, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2667032901704588, "learning_rate": 1.2364179734706382e-06, "loss": 0.2439, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.2632763711895969, "learning_rate": 1.2169167247729852e-06, "loss": 0.2642, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.24987591829192066, "learning_rate": 1.1975656651086864e-06, "loss": 0.2575, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.2739927354855306, "learning_rate": 1.1783649492082926e-06, "loss": 0.2556, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.26526283606913303, "learning_rate": 1.1593147306002183e-06, "loss": 0.2483, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.25214620207568783, "learning_rate": 1.140415161609505e-06, "loss": 0.2628, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.27058015710664296, "learning_rate": 1.121666393356604e-06, "loss": 0.257, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2588405614114247, "learning_rate": 1.1030685757561632e-06, "loss": 0.2615, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2567852674462909, "learning_rate": 1.0846218575158373e-06, "loss": 0.2667, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.2573578440503547, "learning_rate": 1.066326386135097e-06, "loss": 0.2616, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.264896450853199, "learning_rate": 1.0481823079040398e-06, "loss": 0.2577, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.24945121614906346, "learning_rate": 1.0301897679022344e-06, "loss": 0.2547, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.2643075631819673, "learning_rate": 1.0123489099975491e-06, "loss": 0.2523, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.271277141764649, "learning_rate": 9.9465987684501e-07, "loss": 0.2603, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.2667679669413423, "learning_rate": 9.771228098856534e-07, "loss": 0.2608, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.2622332772346231, "learning_rate": 9.597378493454013e-07, "loss": 0.273, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.262648661742412, "learning_rate": 9.425051342339353e-07, "loss": 0.2612, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.250482908703941, "learning_rate": 9.254248023435864e-07, "loss": 0.2495, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.24237301865414995, "learning_rate": 9.084969902482288e-07, "loss": 0.2591, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.26333716915567285, "learning_rate": 8.917218333021993e-07, "loss": 0.2506, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.26726070244618555, "learning_rate": 8.750994656392109e-07, "loss": 0.2612, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.26685689283260117, "learning_rate": 8.58630020171265e-07, "loss": 0.2477, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2662717203545114, "learning_rate": 8.423136285876099e-07, "loss": 0.2567, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2557057996560034, "learning_rate": 8.26150421353682e-07, "loss": 0.2524, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2667566629577879, "learning_rate": 8.101405277100549e-07, "loss": 0.2686, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2713555351347331, "learning_rate": 7.942840756714077e-07, "loss": 0.2654, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.2690515023986757, "learning_rate": 7.785811920255093e-07, "loss": 0.2575, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.266305890042633, "learning_rate": 7.630320023322024e-07, "loss": 0.2604, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.26228196841302565, "learning_rate": 7.476366309223903e-07, "loss": 0.2679, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.2592201865226158, "learning_rate": 7.323952008970537e-07, "loss": 0.2675, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2662604872374954, "learning_rate": 7.173078341262618e-07, "loss": 0.2476, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2590721800818718, "learning_rate": 7.023746512481989e-07, "loss": 0.2598, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.27306195501259856, "learning_rate": 6.875957716681902e-07, "loss": 0.262, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.2639480327402194, "learning_rate": 6.729713135577687e-07, "loss": 0.2475, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.27594702796198645, "learning_rate": 6.585013938537143e-07, "loss": 0.2614, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2718406789647316, "learning_rate": 6.441861282571115e-07, "loss": 0.2795, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.2674423795058646, "learning_rate": 6.300256312324471e-07, "loss": 0.274, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.27282767763226484, "learning_rate": 6.160200160066776e-07, "loss": 0.253, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.2720640537202874, "learning_rate": 6.021693945683327e-07, "loss": 0.2645, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.26512642807933057, "learning_rate": 5.884738776666044e-07, "loss": 0.2675, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.26348291774036176, "learning_rate": 5.749335748104878e-07, "loss": 0.2731, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.2619218523653693, "learning_rate": 5.615485942678778e-07, "loss": 0.2675, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.2722109897183049, "learning_rate": 5.483190430647289e-07, "loss": 0.2519, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.25955228549814785, "learning_rate": 5.352450269841747e-07, "loss": 0.2507, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.2580102166854994, "learning_rate": 5.22326650565701e-07, "loss": 0.2633, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2772274579324782, "learning_rate": 5.095640171043048e-07, "loss": 0.2602, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.2666311221409534, "learning_rate": 4.969572286496594e-07, "loss": 0.249, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.2665578168254885, "learning_rate": 4.845063860053079e-07, "loss": 0.27, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2567448199646521, "learning_rate": 4.7221158872785997e-07, "loss": 0.2534, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.26684631254051494, "learning_rate": 4.600729351261857e-07, "loss": 0.251, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.2656796643111626, "learning_rate": 4.4809052226063355e-07, "loss": 0.2619, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.25014334700704915, "learning_rate": 4.3626444594226046e-07, "loss": 0.2602, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.26253929825118294, "learning_rate": 4.245948007320588e-07, "loss": 0.2689, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.2573132145934711, "learning_rate": 4.130816799401971e-07, "loss": 0.2645, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.26548154388802825, "learning_rate": 4.017251756252827e-07, "loss": 0.2537, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.2639749166968247, "learning_rate": 3.9052537859362473e-07, "loss": 0.2666, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2660360166857703, "learning_rate": 3.7948237839849687e-07, "loss": 0.2569, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.2618437871102257, "learning_rate": 3.6859626333943797e-07, "loss": 0.2518, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.24993895472435715, "learning_rate": 3.578671204615347e-07, "loss": 0.2466, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.26004878924364044, "learning_rate": 3.472950355547267e-07, "loss": 0.2563, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.2447102390295806, "learning_rate": 3.3688009315312244e-07, "loss": 0.2544, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.25905895958822456, "learning_rate": 3.266223765343224e-07, "loss": 0.2576, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2654815808600612, "learning_rate": 3.16521967718757e-07, "loss": 0.2664, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.2763764069675323, "learning_rate": 3.0657894746902726e-07, "loss": 0.2709, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.24644589051875823, "learning_rate": 2.9679339528925654e-07, "loss": 0.2638, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.25328103211262404, "learning_rate": 2.871653894244597e-07, "loss": 0.2669, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.26198051680690654, "learning_rate": 2.7769500685991266e-07, "loss": 0.2419, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2664216610230323, "learning_rate": 2.683823233205485e-07, "loss": 0.2565, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.24797645404153215, "learning_rate": 2.592274132703287e-07, "loss": 0.272, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.26156607842722, "learning_rate": 2.502303499116754e-07, "loss": 0.2632, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.27148610267639384, "learning_rate": 2.413912051848666e-07, "loss": 0.2561, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.25217229456827306, "learning_rate": 2.3271004976746613e-07, "loss": 0.2574, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2450651671720419, "learning_rate": 2.2418695307376393e-07, "loss": 0.2637, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.26809019438221615, "learning_rate": 2.1582198325420968e-07, "loss": 0.2449, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.2703714183155094, "learning_rate": 2.0761520719488447e-07, "loss": 0.2417, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.259550293472362, "learning_rate": 1.9956669051694798e-07, "loss": 0.271, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.250676138094577, "learning_rate": 1.916764975761254e-07, "loss": 0.2567, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2647467032304126, "learning_rate": 1.839446914621923e-07, "loss": 0.2596, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.2546226442968676, "learning_rate": 1.7637133399845962e-07, "loss": 0.2652, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.2501594196558361, "learning_rate": 1.6895648574129397e-07, "loss": 0.2537, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.26809937612492823, "learning_rate": 1.6170020597962465e-07, "loss": 0.2587, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.2521270079238505, "learning_rate": 1.5460255273447078e-07, "loss": 0.2774, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.25045454968051084, "learning_rate": 1.4766358275847715e-07, "loss": 0.2681, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.26915421054487665, "learning_rate": 1.4088335153546573e-07, "loss": 0.2597, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.26713646523611256, "learning_rate": 1.3426191327998496e-07, "loss": 0.2619, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.2525949853306286, "learning_rate": 1.277993209368744e-07, "loss": 0.2622, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.269930284257068, "learning_rate": 1.214956261808542e-07, "loss": 0.2633, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.2576770632782357, "learning_rate": 1.1535087941609846e-07, "loss": 0.2625, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.2626344863191174, "learning_rate": 1.0936512977583802e-07, "loss": 0.2508, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.26576776049032597, "learning_rate": 1.0353842512196732e-07, "loss": 0.2612, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.2690941222822419, "learning_rate": 9.787081204466253e-08, "loss": 0.2643, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2517868739952917, "learning_rate": 9.236233586200627e-08, "loss": 0.2438, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2504750465981248, "learning_rate": 8.70130406196279e-08, "loss": 0.265, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2556789686789269, "learning_rate": 8.182296909035047e-08, "loss": 0.2509, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.2631085715813889, "learning_rate": 7.679216277384439e-08, "loss": 0.2524, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.26644847470470184, "learning_rate": 7.19206618963053e-08, "loss": 0.2591, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.26063732747615254, "learning_rate": 6.720850541012347e-08, "loss": 0.2556, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.254123751002167, "learning_rate": 6.265573099357714e-08, "loss": 0.2405, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.2614763463466017, "learning_rate": 5.826237505053067e-08, "loss": 0.2591, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.2571874438289156, "learning_rate": 5.4028472710137e-08, "loss": 0.2541, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.2625555325454195, "learning_rate": 4.9954057826571146e-08, "loss": 0.2631, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2568618359285923, "learning_rate": 4.6039162978743776e-08, "loss": 0.2496, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.26624311894599084, "learning_rate": 4.228381947004812e-08, "loss": 0.2584, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.2726256908904141, "learning_rate": 3.868805732811343e-08, "loss": 0.2571, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.2594259990849812, "learning_rate": 3.525190530455636e-08, "loss": 0.2707, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.2537347579731422, "learning_rate": 3.197539087475887e-08, "loss": 0.2676, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2663741245463269, "learning_rate": 2.8858540237641786e-08, "loss": 0.2613, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.2627760105049193, "learning_rate": 2.5901378315458247e-08, "loss": 0.2666, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.25054731405461106, "learning_rate": 2.3103928753598347e-08, "loss": 0.2549, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.2636714152498135, "learning_rate": 2.0466213920393718e-08, "loss": 0.2684, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.31308553404297634, "learning_rate": 1.7988254906942115e-08, "loss": 0.2654, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.2595773943465033, "learning_rate": 1.5670071526936447e-08, "loss": 0.2671, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2657995933601985, "learning_rate": 1.3511682316509344e-08, "loss": 0.2597, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.27060509119397896, "learning_rate": 1.1513104534086605e-08, "loss": 0.2555, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.24848188154281978, "learning_rate": 9.67435416023843e-09, "loss": 0.2624, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.2552208854580071, "learning_rate": 7.995445897566178e-09, "loss": 0.2487, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.2726260915609432, "learning_rate": 6.476393170578021e-09, "loss": 0.2577, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.27487058666186587, "learning_rate": 5.11720812557348e-09, "loss": 0.2421, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.26491067123993656, "learning_rate": 3.917901630563492e-09, "loss": 0.2542, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.26730986487395664, "learning_rate": 2.878483275170485e-09, "loss": 0.2556, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.2651329850758385, "learning_rate": 1.998961370555108e-09, "loss": 0.2603, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.26608956671028, "learning_rate": 1.2793429493518361e-09, "loss": 0.2643, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.26459692941554314, "learning_rate": 7.196337656112384e-10, "loss": 0.2605, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.2551443244610752, "learning_rate": 3.198382947511292e-10, "loss": 0.2723, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.2506393117449123, "learning_rate": 7.995973352770137e-11, "loss": 0.2602, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.2568536990859895, "learning_rate": 0.0, "loss": 0.2552, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 2564837740773376.0, "train_loss": 0.45295593604626444, "train_runtime": 27969.5706, "train_samples_per_second": 5.649, "train_steps_per_second": 0.044 } ], "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": 2564837740773376.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }