{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 3086, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0032404406999351912, "grad_norm": 13.30365312552572, "learning_rate": 1.4563106796116507e-07, "loss": 0.5576, "step": 10 }, { "epoch": 0.0064808813998703824, "grad_norm": 14.204922777466475, "learning_rate": 3.074433656957929e-07, "loss": 0.5525, "step": 20 }, { "epoch": 0.009721322099805573, "grad_norm": 9.138075119736614, "learning_rate": 4.6925566343042074e-07, "loss": 0.5424, "step": 30 }, { "epoch": 0.012961762799740765, "grad_norm": 5.051726436122705, "learning_rate": 6.310679611650486e-07, "loss": 0.5232, "step": 40 }, { "epoch": 0.016202203499675955, "grad_norm": 3.46444651483391, "learning_rate": 7.928802588996765e-07, "loss": 0.4552, "step": 50 }, { "epoch": 0.019442644199611146, "grad_norm": 1.6233777031065288, "learning_rate": 9.546925566343043e-07, "loss": 0.3873, "step": 60 }, { "epoch": 0.02268308489954634, "grad_norm": 1.1762000179825056, "learning_rate": 1.1165048543689322e-06, "loss": 0.3333, "step": 70 }, { "epoch": 0.02592352559948153, "grad_norm": 0.9558551467742782, "learning_rate": 1.27831715210356e-06, "loss": 0.2982, "step": 80 }, { "epoch": 0.02916396629941672, "grad_norm": 0.9422801874700582, "learning_rate": 1.440129449838188e-06, "loss": 0.2797, "step": 90 }, { "epoch": 0.03240440699935191, "grad_norm": 0.8214754997776478, "learning_rate": 1.6019417475728158e-06, "loss": 0.2596, "step": 100 }, { "epoch": 0.0356448476992871, "grad_norm": 0.9532933362931321, "learning_rate": 1.7637540453074433e-06, "loss": 0.2563, "step": 110 }, { "epoch": 0.03888528839922229, "grad_norm": 0.9390014348115954, "learning_rate": 1.925566343042071e-06, "loss": 0.2492, "step": 120 }, { "epoch": 0.04212572909915749, "grad_norm": 0.8940098493565622, "learning_rate": 2.0873786407766993e-06, "loss": 0.2451, "step": 130 }, { "epoch": 0.04536616979909268, "grad_norm": 0.956678618390739, "learning_rate": 2.249190938511327e-06, "loss": 0.2408, "step": 140 }, { "epoch": 0.04860661049902787, "grad_norm": 0.9610225933792697, "learning_rate": 2.411003236245955e-06, "loss": 0.236, "step": 150 }, { "epoch": 0.05184705119896306, "grad_norm": 0.9269340800650678, "learning_rate": 2.5728155339805826e-06, "loss": 0.2246, "step": 160 }, { "epoch": 0.05508749189889825, "grad_norm": 0.9180868113485474, "learning_rate": 2.7346278317152108e-06, "loss": 0.2213, "step": 170 }, { "epoch": 0.05832793259883344, "grad_norm": 0.9786641616216852, "learning_rate": 2.8964401294498386e-06, "loss": 0.2166, "step": 180 }, { "epoch": 0.06156837329876863, "grad_norm": 0.980551217904519, "learning_rate": 3.058252427184466e-06, "loss": 0.2119, "step": 190 }, { "epoch": 0.06480881399870382, "grad_norm": 0.8626959550478579, "learning_rate": 3.220064724919094e-06, "loss": 0.2106, "step": 200 }, { "epoch": 0.06804925469863901, "grad_norm": 0.8489552811589715, "learning_rate": 3.381877022653722e-06, "loss": 0.2112, "step": 210 }, { "epoch": 0.0712896953985742, "grad_norm": 0.8916159222304701, "learning_rate": 3.54368932038835e-06, "loss": 0.2042, "step": 220 }, { "epoch": 0.07453013609850939, "grad_norm": 0.9086960370554139, "learning_rate": 3.7055016181229774e-06, "loss": 0.1979, "step": 230 }, { "epoch": 0.07777057679844458, "grad_norm": 0.8413464808652309, "learning_rate": 3.867313915857606e-06, "loss": 0.1992, "step": 240 }, { "epoch": 0.08101101749837979, "grad_norm": 0.8989628261518818, "learning_rate": 4.029126213592233e-06, "loss": 0.1968, "step": 250 }, { "epoch": 0.08425145819831498, "grad_norm": 0.9955980487760288, "learning_rate": 4.190938511326861e-06, "loss": 0.188, "step": 260 }, { "epoch": 0.08749189889825017, "grad_norm": 0.9206294362335926, "learning_rate": 4.352750809061489e-06, "loss": 0.1869, "step": 270 }, { "epoch": 0.09073233959818536, "grad_norm": 0.8143016067643809, "learning_rate": 4.514563106796117e-06, "loss": 0.1873, "step": 280 }, { "epoch": 0.09397278029812055, "grad_norm": 0.840197832466951, "learning_rate": 4.676375404530745e-06, "loss": 0.1832, "step": 290 }, { "epoch": 0.09721322099805574, "grad_norm": 0.8031811731017143, "learning_rate": 4.838187702265373e-06, "loss": 0.1792, "step": 300 }, { "epoch": 0.10045366169799093, "grad_norm": 0.7566604882873896, "learning_rate": 5e-06, "loss": 0.1741, "step": 310 }, { "epoch": 0.10369410239792612, "grad_norm": 0.6800771883014759, "learning_rate": 4.999840024540205e-06, "loss": 0.1684, "step": 320 }, { "epoch": 0.10693454309786131, "grad_norm": 0.5814963126209718, "learning_rate": 4.999360118634534e-06, "loss": 0.1685, "step": 330 }, { "epoch": 0.1101749837977965, "grad_norm": 0.5139919383970122, "learning_rate": 4.998560343701524e-06, "loss": 0.1656, "step": 340 }, { "epoch": 0.11341542449773169, "grad_norm": 0.4719697466406009, "learning_rate": 4.997440802096665e-06, "loss": 0.1662, "step": 350 }, { "epoch": 0.11665586519766688, "grad_norm": 0.5441236604152835, "learning_rate": 4.996001637099303e-06, "loss": 0.1571, "step": 360 }, { "epoch": 0.11989630589760207, "grad_norm": 0.5924545330957118, "learning_rate": 4.994243032894303e-06, "loss": 0.1618, "step": 370 }, { "epoch": 0.12313674659753726, "grad_norm": 0.4776889270665497, "learning_rate": 4.992165214548479e-06, "loss": 0.165, "step": 380 }, { "epoch": 0.12637718729747247, "grad_norm": 0.4865661174720737, "learning_rate": 4.989768447981786e-06, "loss": 0.1631, "step": 390 }, { "epoch": 0.12961762799740764, "grad_norm": 0.39533484163777743, "learning_rate": 4.987053039933294e-06, "loss": 0.1631, "step": 400 }, { "epoch": 0.13285806869734285, "grad_norm": 0.4194333976090903, "learning_rate": 4.984019337921919e-06, "loss": 0.1596, "step": 410 }, { "epoch": 0.13609850939727802, "grad_norm": 0.417606467091398, "learning_rate": 4.980667730201964e-06, "loss": 0.1622, "step": 420 }, { "epoch": 0.13933895009721323, "grad_norm": 0.4135543560101031, "learning_rate": 4.976998645713417e-06, "loss": 0.1626, "step": 430 }, { "epoch": 0.1425793907971484, "grad_norm": 0.3863220511507732, "learning_rate": 4.973012554027059e-06, "loss": 0.1563, "step": 440 }, { "epoch": 0.1458198314970836, "grad_norm": 0.4057624631990764, "learning_rate": 4.968709965284373e-06, "loss": 0.1601, "step": 450 }, { "epoch": 0.14906027219701878, "grad_norm": 0.43679600565915516, "learning_rate": 4.964091430132246e-06, "loss": 0.1571, "step": 460 }, { "epoch": 0.152300712896954, "grad_norm": 0.410392605815529, "learning_rate": 4.959157539652507e-06, "loss": 0.1578, "step": 470 }, { "epoch": 0.15554115359688916, "grad_norm": 0.4269387014050368, "learning_rate": 4.9539089252862745e-06, "loss": 0.1564, "step": 480 }, { "epoch": 0.15878159429682437, "grad_norm": 0.3867586094696986, "learning_rate": 4.948346258753147e-06, "loss": 0.157, "step": 490 }, { "epoch": 0.16202203499675957, "grad_norm": 0.371324732751771, "learning_rate": 4.942470251965232e-06, "loss": 0.1555, "step": 500 }, { "epoch": 0.16526247569669475, "grad_norm": 0.38710422014101686, "learning_rate": 4.936281656936038e-06, "loss": 0.1536, "step": 510 }, { "epoch": 0.16850291639662995, "grad_norm": 0.396987101322912, "learning_rate": 4.929781265684237e-06, "loss": 0.1572, "step": 520 }, { "epoch": 0.17174335709656513, "grad_norm": 0.4019858569286597, "learning_rate": 4.92296991013229e-06, "loss": 0.1578, "step": 530 }, { "epoch": 0.17498379779650033, "grad_norm": 0.38858464136588106, "learning_rate": 4.915848461999987e-06, "loss": 0.155, "step": 540 }, { "epoch": 0.1782242384964355, "grad_norm": 0.4114170865581837, "learning_rate": 4.908417832692879e-06, "loss": 0.1539, "step": 550 }, { "epoch": 0.18146467919637072, "grad_norm": 0.40190769617100247, "learning_rate": 4.900678973185638e-06, "loss": 0.1493, "step": 560 }, { "epoch": 0.1847051198963059, "grad_norm": 0.3776026088033294, "learning_rate": 4.892632873900349e-06, "loss": 0.1571, "step": 570 }, { "epoch": 0.1879455605962411, "grad_norm": 0.3872354376930627, "learning_rate": 4.884280564579761e-06, "loss": 0.1546, "step": 580 }, { "epoch": 0.19118600129617627, "grad_norm": 0.40614075304432395, "learning_rate": 4.8756231141554925e-06, "loss": 0.1523, "step": 590 }, { "epoch": 0.19442644199611148, "grad_norm": 0.3841160702323512, "learning_rate": 4.866661630611231e-06, "loss": 0.1497, "step": 600 }, { "epoch": 0.19766688269604665, "grad_norm": 0.37858054721421236, "learning_rate": 4.8573972608409395e-06, "loss": 0.1569, "step": 610 }, { "epoch": 0.20090732339598186, "grad_norm": 0.4017068446743905, "learning_rate": 4.847831190502068e-06, "loss": 0.1506, "step": 620 }, { "epoch": 0.20414776409591703, "grad_norm": 0.386610704005529, "learning_rate": 4.837964643863818e-06, "loss": 0.1552, "step": 630 }, { "epoch": 0.20738820479585224, "grad_norm": 0.3611796883060248, "learning_rate": 4.827798883650455e-06, "loss": 0.1528, "step": 640 }, { "epoch": 0.21062864549578741, "grad_norm": 0.36233797273951096, "learning_rate": 4.817335210879712e-06, "loss": 0.1537, "step": 650 }, { "epoch": 0.21386908619572262, "grad_norm": 0.355034084310162, "learning_rate": 4.8065749646962815e-06, "loss": 0.1482, "step": 660 }, { "epoch": 0.21710952689565782, "grad_norm": 0.3714493090743044, "learning_rate": 4.795519522200424e-06, "loss": 0.1524, "step": 670 }, { "epoch": 0.220349967595593, "grad_norm": 0.3595872341149548, "learning_rate": 4.784170298271739e-06, "loss": 0.1537, "step": 680 }, { "epoch": 0.2235904082955282, "grad_norm": 0.3657197570676038, "learning_rate": 4.772528745388079e-06, "loss": 0.1496, "step": 690 }, { "epoch": 0.22683084899546338, "grad_norm": 0.39757465881991577, "learning_rate": 4.760596353439665e-06, "loss": 0.1476, "step": 700 }, { "epoch": 0.23007128969539858, "grad_norm": 0.3725684613588135, "learning_rate": 4.748374649538406e-06, "loss": 0.1505, "step": 710 }, { "epoch": 0.23331173039533376, "grad_norm": 0.373958535247375, "learning_rate": 4.735865197822465e-06, "loss": 0.1521, "step": 720 }, { "epoch": 0.23655217109526896, "grad_norm": 0.3895028323791198, "learning_rate": 4.7230695992560725e-06, "loss": 0.1477, "step": 730 }, { "epoch": 0.23979261179520414, "grad_norm": 0.362297190858576, "learning_rate": 4.709989491424641e-06, "loss": 0.1487, "step": 740 }, { "epoch": 0.24303305249513935, "grad_norm": 0.3501236992769411, "learning_rate": 4.69662654832518e-06, "loss": 0.1511, "step": 750 }, { "epoch": 0.24627349319507452, "grad_norm": 0.396141744926481, "learning_rate": 4.682982480152066e-06, "loss": 0.1545, "step": 760 }, { "epoch": 0.24951393389500973, "grad_norm": 0.386092381571303, "learning_rate": 4.669059033078159e-06, "loss": 0.1548, "step": 770 }, { "epoch": 0.25275437459494493, "grad_norm": 0.37841627886408896, "learning_rate": 4.65485798903134e-06, "loss": 0.1467, "step": 780 }, { "epoch": 0.2559948152948801, "grad_norm": 0.3790829553236213, "learning_rate": 4.640381165466447e-06, "loss": 0.1458, "step": 790 }, { "epoch": 0.2592352559948153, "grad_norm": 0.3676425416717676, "learning_rate": 4.625630415132688e-06, "loss": 0.1519, "step": 800 }, { "epoch": 0.26247569669475046, "grad_norm": 0.4020941562750785, "learning_rate": 4.610607625836515e-06, "loss": 0.1476, "step": 810 }, { "epoch": 0.2657161373946857, "grad_norm": 0.36503070299017704, "learning_rate": 4.595314720200028e-06, "loss": 0.1469, "step": 820 }, { "epoch": 0.26895657809462087, "grad_norm": 0.3621589576589696, "learning_rate": 4.579753655414916e-06, "loss": 0.1469, "step": 830 }, { "epoch": 0.27219701879455604, "grad_norm": 0.38775207709700354, "learning_rate": 4.563926422991973e-06, "loss": 0.1507, "step": 840 }, { "epoch": 0.2754374594944913, "grad_norm": 0.3808349919379576, "learning_rate": 4.5478350485062275e-06, "loss": 0.1505, "step": 850 }, { "epoch": 0.27867790019442645, "grad_norm": 0.41092711058175224, "learning_rate": 4.531481591337706e-06, "loss": 0.1465, "step": 860 }, { "epoch": 0.28191834089436163, "grad_norm": 0.3677672974804986, "learning_rate": 4.51486814440787e-06, "loss": 0.1497, "step": 870 }, { "epoch": 0.2851587815942968, "grad_norm": 0.3623506682005845, "learning_rate": 4.497996833911771e-06, "loss": 0.1494, "step": 880 }, { "epoch": 0.28839922229423204, "grad_norm": 0.37070206947839884, "learning_rate": 4.48086981904593e-06, "loss": 0.1543, "step": 890 }, { "epoch": 0.2916396629941672, "grad_norm": 0.3639901651185149, "learning_rate": 4.463489291732011e-06, "loss": 0.1414, "step": 900 }, { "epoch": 0.2948801036941024, "grad_norm": 0.3559919942818163, "learning_rate": 4.445857476336292e-06, "loss": 0.1486, "step": 910 }, { "epoch": 0.29812054439403757, "grad_norm": 0.38283982373110453, "learning_rate": 4.427976629384994e-06, "loss": 0.1465, "step": 920 }, { "epoch": 0.3013609850939728, "grad_norm": 0.37801217199677106, "learning_rate": 4.409849039275486e-06, "loss": 0.1468, "step": 930 }, { "epoch": 0.304601425793908, "grad_norm": 0.4096620960705283, "learning_rate": 4.391477025983418e-06, "loss": 0.1479, "step": 940 }, { "epoch": 0.30784186649384315, "grad_norm": 0.3604056272858565, "learning_rate": 4.372862940765811e-06, "loss": 0.1496, "step": 950 }, { "epoch": 0.31108230719377833, "grad_norm": 0.3538536423133527, "learning_rate": 4.354009165860136e-06, "loss": 0.1482, "step": 960 }, { "epoch": 0.31432274789371356, "grad_norm": 0.3904102444609031, "learning_rate": 4.3349181141794414e-06, "loss": 0.1435, "step": 970 }, { "epoch": 0.31756318859364874, "grad_norm": 0.3859901702462496, "learning_rate": 4.315592229003544e-06, "loss": 0.1456, "step": 980 }, { "epoch": 0.3208036292935839, "grad_norm": 0.35852358880201146, "learning_rate": 4.2960339836663364e-06, "loss": 0.145, "step": 990 }, { "epoch": 0.32404406999351915, "grad_norm": 0.3565242267972036, "learning_rate": 4.276245881239253e-06, "loss": 0.1466, "step": 1000 }, { "epoch": 0.3272845106934543, "grad_norm": 0.3433337357670066, "learning_rate": 4.2562304542109186e-06, "loss": 0.1439, "step": 1010 }, { "epoch": 0.3305249513933895, "grad_norm": 0.38264147572948926, "learning_rate": 4.235990264163048e-06, "loss": 0.1442, "step": 1020 }, { "epoch": 0.3337653920933247, "grad_norm": 0.36500282997002936, "learning_rate": 4.215527901442609e-06, "loss": 0.1433, "step": 1030 }, { "epoch": 0.3370058327932599, "grad_norm": 0.3846660553174048, "learning_rate": 4.194845984830308e-06, "loss": 0.1474, "step": 1040 }, { "epoch": 0.3402462734931951, "grad_norm": 0.37675710340654855, "learning_rate": 4.173947161205443e-06, "loss": 0.149, "step": 1050 }, { "epoch": 0.34348671419313026, "grad_norm": 0.36661580250234177, "learning_rate": 4.152834105207146e-06, "loss": 0.1448, "step": 1060 }, { "epoch": 0.34672715489306544, "grad_norm": 0.37636552154818864, "learning_rate": 4.131509518892093e-06, "loss": 0.1454, "step": 1070 }, { "epoch": 0.34996759559300067, "grad_norm": 0.3581018731822282, "learning_rate": 4.109976131388682e-06, "loss": 0.1469, "step": 1080 }, { "epoch": 0.35320803629293585, "grad_norm": 0.3387824669850879, "learning_rate": 4.088236698547767e-06, "loss": 0.1453, "step": 1090 }, { "epoch": 0.356448476992871, "grad_norm": 0.3691931165432145, "learning_rate": 4.06629400258996e-06, "loss": 0.1466, "step": 1100 }, { "epoch": 0.3596889176928062, "grad_norm": 0.34829825491346456, "learning_rate": 4.0441508517495605e-06, "loss": 0.1449, "step": 1110 }, { "epoch": 0.36292935839274143, "grad_norm": 0.38098751196774483, "learning_rate": 4.021810079915159e-06, "loss": 0.1466, "step": 1120 }, { "epoch": 0.3661697990926766, "grad_norm": 0.3742527627607329, "learning_rate": 3.9992745462669515e-06, "loss": 0.1467, "step": 1130 }, { "epoch": 0.3694102397926118, "grad_norm": 0.3905850349665511, "learning_rate": 3.976547134910826e-06, "loss": 0.1452, "step": 1140 }, { "epoch": 0.37265068049254696, "grad_norm": 0.332721575400441, "learning_rate": 3.953630754509245e-06, "loss": 0.1478, "step": 1150 }, { "epoch": 0.3758911211924822, "grad_norm": 0.34472432311127355, "learning_rate": 3.930528337909002e-06, "loss": 0.1466, "step": 1160 }, { "epoch": 0.37913156189241737, "grad_norm": 0.3742114947748869, "learning_rate": 3.907242841765874e-06, "loss": 0.1475, "step": 1170 }, { "epoch": 0.38237200259235254, "grad_norm": 0.363030396921668, "learning_rate": 3.883777246166219e-06, "loss": 0.1386, "step": 1180 }, { "epoch": 0.3856124432922878, "grad_norm": 0.36210921666900014, "learning_rate": 3.860134554245597e-06, "loss": 0.1412, "step": 1190 }, { "epoch": 0.38885288399222295, "grad_norm": 0.3599182096747789, "learning_rate": 3.836317791804415e-06, "loss": 0.1408, "step": 1200 }, { "epoch": 0.39209332469215813, "grad_norm": 0.40331300021325894, "learning_rate": 3.81233000692069e-06, "loss": 0.1428, "step": 1210 }, { "epoch": 0.3953337653920933, "grad_norm": 0.34914858021538103, "learning_rate": 3.7881742695599567e-06, "loss": 0.1439, "step": 1220 }, { "epoch": 0.39857420609202854, "grad_norm": 0.3637051905577843, "learning_rate": 3.763853671182367e-06, "loss": 0.1445, "step": 1230 }, { "epoch": 0.4018146467919637, "grad_norm": 0.3560295518397911, "learning_rate": 3.7393713243470475e-06, "loss": 0.1426, "step": 1240 }, { "epoch": 0.4050550874918989, "grad_norm": 0.37115109403035373, "learning_rate": 3.7147303623137508e-06, "loss": 0.1438, "step": 1250 }, { "epoch": 0.40829552819183407, "grad_norm": 0.36713310156131235, "learning_rate": 3.6899339386418635e-06, "loss": 0.1433, "step": 1260 }, { "epoch": 0.4115359688917693, "grad_norm": 0.3739701552036908, "learning_rate": 3.664985226786807e-06, "loss": 0.1415, "step": 1270 }, { "epoch": 0.4147764095917045, "grad_norm": 0.4018803004726532, "learning_rate": 3.6398874196939015e-06, "loss": 0.1424, "step": 1280 }, { "epoch": 0.41801685029163965, "grad_norm": 0.3856228913000613, "learning_rate": 3.614643729389731e-06, "loss": 0.1434, "step": 1290 }, { "epoch": 0.42125729099157483, "grad_norm": 0.3590367113459008, "learning_rate": 3.5892573865710665e-06, "loss": 0.1447, "step": 1300 }, { "epoch": 0.42449773169151006, "grad_norm": 0.35395438465776946, "learning_rate": 3.5637316401913997e-06, "loss": 0.1432, "step": 1310 }, { "epoch": 0.42773817239144524, "grad_norm": 0.35628640020346514, "learning_rate": 3.5380697570451413e-06, "loss": 0.1404, "step": 1320 }, { "epoch": 0.4309786130913804, "grad_norm": 0.36552890562756624, "learning_rate": 3.5122750213495355e-06, "loss": 0.1456, "step": 1330 }, { "epoch": 0.43421905379131565, "grad_norm": 0.37173141387082576, "learning_rate": 3.486350734324346e-06, "loss": 0.1435, "step": 1340 }, { "epoch": 0.4374594944912508, "grad_norm": 0.3539914127253098, "learning_rate": 3.460300213769361e-06, "loss": 0.1427, "step": 1350 }, { "epoch": 0.440699935191186, "grad_norm": 0.3619461607830295, "learning_rate": 3.4341267936397843e-06, "loss": 0.1403, "step": 1360 }, { "epoch": 0.4439403758911212, "grad_norm": 0.35261727478654553, "learning_rate": 3.4078338236195506e-06, "loss": 0.1419, "step": 1370 }, { "epoch": 0.4471808165910564, "grad_norm": 0.3320165163284001, "learning_rate": 3.3814246686926367e-06, "loss": 0.1422, "step": 1380 }, { "epoch": 0.4504212572909916, "grad_norm": 0.3505007893913486, "learning_rate": 3.354902708712402e-06, "loss": 0.1415, "step": 1390 }, { "epoch": 0.45366169799092676, "grad_norm": 0.366809997754886, "learning_rate": 3.3282713379690418e-06, "loss": 0.1423, "step": 1400 }, { "epoch": 0.45690213869086194, "grad_norm": 0.37510389340397243, "learning_rate": 3.301533964755179e-06, "loss": 0.144, "step": 1410 }, { "epoch": 0.46014257939079717, "grad_norm": 0.3751915143045206, "learning_rate": 3.2746940109296744e-06, "loss": 0.143, "step": 1420 }, { "epoch": 0.46338302009073234, "grad_norm": 0.34874611917779574, "learning_rate": 3.2477549114796892e-06, "loss": 0.1433, "step": 1430 }, { "epoch": 0.4666234607906675, "grad_norm": 0.34401160771032996, "learning_rate": 3.220720114081081e-06, "loss": 0.1429, "step": 1440 }, { "epoch": 0.4698639014906027, "grad_norm": 0.34265687524195426, "learning_rate": 3.193593078657165e-06, "loss": 0.1447, "step": 1450 }, { "epoch": 0.47310434219053793, "grad_norm": 0.36594432029338536, "learning_rate": 3.1663772769359134e-06, "loss": 0.1417, "step": 1460 }, { "epoch": 0.4763447828904731, "grad_norm": 0.4010466659928031, "learning_rate": 3.1390761920056423e-06, "loss": 0.1449, "step": 1470 }, { "epoch": 0.4795852235904083, "grad_norm": 0.38421005144265497, "learning_rate": 3.111693317869241e-06, "loss": 0.1415, "step": 1480 }, { "epoch": 0.48282566429034346, "grad_norm": 0.3405551521124088, "learning_rate": 3.084232158997017e-06, "loss": 0.1416, "step": 1490 }, { "epoch": 0.4860661049902787, "grad_norm": 0.34368244054627933, "learning_rate": 3.0566962298781822e-06, "loss": 0.1366, "step": 1500 }, { "epoch": 0.48930654569021387, "grad_norm": 0.3475737652432212, "learning_rate": 3.0290890545710732e-06, "loss": 0.1427, "step": 1510 }, { "epoch": 0.49254698639014904, "grad_norm": 0.3915309068687966, "learning_rate": 3.0014141662521423e-06, "loss": 0.142, "step": 1520 }, { "epoch": 0.4957874270900843, "grad_norm": 0.38245602033100184, "learning_rate": 2.973675106763776e-06, "loss": 0.1482, "step": 1530 }, { "epoch": 0.49902786779001945, "grad_norm": 0.3660718954078658, "learning_rate": 2.9458754261610113e-06, "loss": 0.1382, "step": 1540 }, { "epoch": 0.5022683084899546, "grad_norm": 0.3560275044859087, "learning_rate": 2.9180186822571953e-06, "loss": 0.1397, "step": 1550 }, { "epoch": 0.5055087491898899, "grad_norm": 0.3476891353623016, "learning_rate": 2.8901084401686635e-06, "loss": 0.1399, "step": 1560 }, { "epoch": 0.508749189889825, "grad_norm": 0.36360266266143876, "learning_rate": 2.8621482718584615e-06, "loss": 0.1434, "step": 1570 }, { "epoch": 0.5119896305897602, "grad_norm": 0.3607127979390933, "learning_rate": 2.8341417556792163e-06, "loss": 0.1391, "step": 1580 }, { "epoch": 0.5152300712896954, "grad_norm": 0.36135212438772696, "learning_rate": 2.8060924759151687e-06, "loss": 0.1369, "step": 1590 }, { "epoch": 0.5184705119896306, "grad_norm": 0.36165014897143566, "learning_rate": 2.7780040223234623e-06, "loss": 0.1428, "step": 1600 }, { "epoch": 0.5217109526895658, "grad_norm": 0.3809583977124813, "learning_rate": 2.749879989674718e-06, "loss": 0.1422, "step": 1610 }, { "epoch": 0.5249513933895009, "grad_norm": 0.3385971069870571, "learning_rate": 2.72172397729298e-06, "loss": 0.1356, "step": 1620 }, { "epoch": 0.5281918340894362, "grad_norm": 0.3446592011239239, "learning_rate": 2.6935395885950705e-06, "loss": 0.1421, "step": 1630 }, { "epoch": 0.5314322747893714, "grad_norm": 0.3824673660290881, "learning_rate": 2.665330430629421e-06, "loss": 0.1397, "step": 1640 }, { "epoch": 0.5346727154893065, "grad_norm": 0.3717938840273103, "learning_rate": 2.6371001136144458e-06, "loss": 0.1388, "step": 1650 }, { "epoch": 0.5379131561892417, "grad_norm": 0.3442850639482792, "learning_rate": 2.6088522504764983e-06, "loss": 0.1412, "step": 1660 }, { "epoch": 0.541153596889177, "grad_norm": 0.35531304056249186, "learning_rate": 2.580590456387497e-06, "loss": 0.1392, "step": 1670 }, { "epoch": 0.5443940375891121, "grad_norm": 0.3659296727759621, "learning_rate": 2.5523183483022406e-06, "loss": 0.142, "step": 1680 }, { "epoch": 0.5476344782890473, "grad_norm": 0.3598598578768378, "learning_rate": 2.5240395444955255e-06, "loss": 0.14, "step": 1690 }, { "epoch": 0.5508749189889826, "grad_norm": 0.37315624702714517, "learning_rate": 2.495757664099063e-06, "loss": 0.1422, "step": 1700 }, { "epoch": 0.5541153596889177, "grad_norm": 0.38147815062716345, "learning_rate": 2.4674763266383096e-06, "loss": 0.1399, "step": 1710 }, { "epoch": 0.5573558003888529, "grad_norm": 0.3514332109313319, "learning_rate": 2.439199151569236e-06, "loss": 0.1389, "step": 1720 }, { "epoch": 0.560596241088788, "grad_norm": 0.3466932777873452, "learning_rate": 2.41092975781511e-06, "loss": 0.1364, "step": 1730 }, { "epoch": 0.5638366817887233, "grad_norm": 0.34717040583506037, "learning_rate": 2.382671763303342e-06, "loss": 0.1356, "step": 1740 }, { "epoch": 0.5670771224886585, "grad_norm": 0.37026146298749535, "learning_rate": 2.3544287845024643e-06, "loss": 0.1399, "step": 1750 }, { "epoch": 0.5703175631885936, "grad_norm": 0.3785438614418004, "learning_rate": 2.326204435959291e-06, "loss": 0.1442, "step": 1760 }, { "epoch": 0.5735580038885288, "grad_norm": 0.3809262572423141, "learning_rate": 2.2980023298363334e-06, "loss": 0.142, "step": 1770 }, { "epoch": 0.5767984445884641, "grad_norm": 0.3736610534336298, "learning_rate": 2.2698260754495057e-06, "loss": 0.1386, "step": 1780 }, { "epoch": 0.5800388852883992, "grad_norm": 0.37243260617527046, "learning_rate": 2.2416792788062073e-06, "loss": 0.1379, "step": 1790 }, { "epoch": 0.5832793259883344, "grad_norm": 0.3653198160876884, "learning_rate": 2.213565542143828e-06, "loss": 0.1394, "step": 1800 }, { "epoch": 0.5865197666882696, "grad_norm": 0.3456465195181901, "learning_rate": 2.1854884634687267e-06, "loss": 0.1361, "step": 1810 }, { "epoch": 0.5897602073882048, "grad_norm": 0.35698643784051837, "learning_rate": 2.1574516360957588e-06, "loss": 0.134, "step": 1820 }, { "epoch": 0.59300064808814, "grad_norm": 0.33396274798278874, "learning_rate": 2.129458648188405e-06, "loss": 0.1378, "step": 1830 }, { "epoch": 0.5962410887880751, "grad_norm": 0.35679763524806046, "learning_rate": 2.1015130822995553e-06, "loss": 0.1387, "step": 1840 }, { "epoch": 0.5994815294880104, "grad_norm": 0.3748507983654056, "learning_rate": 2.0736185149130117e-06, "loss": 0.1353, "step": 1850 }, { "epoch": 0.6027219701879456, "grad_norm": 0.3680336654813566, "learning_rate": 2.0457785159857673e-06, "loss": 0.142, "step": 1860 }, { "epoch": 0.6059624108878807, "grad_norm": 0.3461769829954041, "learning_rate": 2.0179966484911268e-06, "loss": 0.1371, "step": 1870 }, { "epoch": 0.609202851587816, "grad_norm": 0.35213432555022733, "learning_rate": 1.990276467962711e-06, "loss": 0.1377, "step": 1880 }, { "epoch": 0.6124432922877512, "grad_norm": 0.3838660410707078, "learning_rate": 1.9626215220394213e-06, "loss": 0.1403, "step": 1890 }, { "epoch": 0.6156837329876863, "grad_norm": 0.394603150983814, "learning_rate": 1.9350353500114072e-06, "loss": 0.1369, "step": 1900 }, { "epoch": 0.6189241736876215, "grad_norm": 0.3327444517938039, "learning_rate": 1.907521482367114e-06, "loss": 0.1406, "step": 1910 }, { "epoch": 0.6221646143875567, "grad_norm": 0.3704170243923683, "learning_rate": 1.8800834403414437e-06, "loss": 0.137, "step": 1920 }, { "epoch": 0.6254050550874919, "grad_norm": 0.40349804036311127, "learning_rate": 1.8527247354651048e-06, "loss": 0.1362, "step": 1930 }, { "epoch": 0.6286454957874271, "grad_norm": 0.364607317668594, "learning_rate": 1.8254488691152145e-06, "loss": 0.1378, "step": 1940 }, { "epoch": 0.6318859364873622, "grad_norm": 0.38797616750444036, "learning_rate": 1.7982593320671793e-06, "loss": 0.1387, "step": 1950 }, { "epoch": 0.6351263771872975, "grad_norm": 0.3943004101702645, "learning_rate": 1.7711596040479523e-06, "loss": 0.1378, "step": 1960 }, { "epoch": 0.6383668178872327, "grad_norm": 0.34986766543947917, "learning_rate": 1.744153153290693e-06, "loss": 0.1382, "step": 1970 }, { "epoch": 0.6416072585871678, "grad_norm": 0.35689489846966777, "learning_rate": 1.717243436090904e-06, "loss": 0.1398, "step": 1980 }, { "epoch": 0.6448476992871031, "grad_norm": 0.358287736012017, "learning_rate": 1.6904338963640913e-06, "loss": 0.1342, "step": 1990 }, { "epoch": 0.6480881399870383, "grad_norm": 0.35009264406089535, "learning_rate": 1.6637279652050103e-06, "loss": 0.1384, "step": 2000 }, { "epoch": 0.6513285806869734, "grad_norm": 0.36264463552008447, "learning_rate": 1.6371290604485532e-06, "loss": 0.1345, "step": 2010 }, { "epoch": 0.6545690213869086, "grad_norm": 0.37898011262102793, "learning_rate": 1.610640586232336e-06, "loss": 0.136, "step": 2020 }, { "epoch": 0.6578094620868438, "grad_norm": 0.3486402988937132, "learning_rate": 1.5842659325610326e-06, "loss": 0.1339, "step": 2030 }, { "epoch": 0.661049902786779, "grad_norm": 0.3494806553044058, "learning_rate": 1.5580084748725193e-06, "loss": 0.132, "step": 2040 }, { "epoch": 0.6642903434867142, "grad_norm": 0.3376036564372793, "learning_rate": 1.5318715736058926e-06, "loss": 0.1419, "step": 2050 }, { "epoch": 0.6675307841866494, "grad_norm": 0.3619041141435384, "learning_rate": 1.5058585737713883e-06, "loss": 0.1377, "step": 2060 }, { "epoch": 0.6707712248865846, "grad_norm": 0.37485938510309685, "learning_rate": 1.4799728045222956e-06, "loss": 0.1373, "step": 2070 }, { "epoch": 0.6740116655865198, "grad_norm": 0.3596734953623062, "learning_rate": 1.4542175787288818e-06, "loss": 0.1396, "step": 2080 }, { "epoch": 0.6772521062864549, "grad_norm": 0.3531801559136217, "learning_rate": 1.428596192554421e-06, "loss": 0.139, "step": 2090 }, { "epoch": 0.6804925469863902, "grad_norm": 0.35403583546745904, "learning_rate": 1.4031119250333393e-06, "loss": 0.1386, "step": 2100 }, { "epoch": 0.6837329876863253, "grad_norm": 0.3499312200329266, "learning_rate": 1.3777680376515667e-06, "loss": 0.138, "step": 2110 }, { "epoch": 0.6869734283862605, "grad_norm": 0.3655179914285288, "learning_rate": 1.3525677739291338e-06, "loss": 0.1374, "step": 2120 }, { "epoch": 0.6902138690861958, "grad_norm": 0.36296013901637053, "learning_rate": 1.3275143590050622e-06, "loss": 0.1391, "step": 2130 }, { "epoch": 0.6934543097861309, "grad_norm": 0.33352013543504444, "learning_rate": 1.3026109992246084e-06, "loss": 0.1356, "step": 2140 }, { "epoch": 0.6966947504860661, "grad_norm": 0.34615241767967, "learning_rate": 1.2778608817289167e-06, "loss": 0.1365, "step": 2150 }, { "epoch": 0.6999351911860013, "grad_norm": 0.36999888059560476, "learning_rate": 1.2532671740471292e-06, "loss": 0.1411, "step": 2160 }, { "epoch": 0.7031756318859365, "grad_norm": 0.34402496133806365, "learning_rate": 1.2288330236910025e-06, "loss": 0.1396, "step": 2170 }, { "epoch": 0.7064160725858717, "grad_norm": 0.35636630900488314, "learning_rate": 1.204561557752085e-06, "loss": 0.1394, "step": 2180 }, { "epoch": 0.7096565132858069, "grad_norm": 0.36181518745129104, "learning_rate": 1.1804558825015172e-06, "loss": 0.1365, "step": 2190 }, { "epoch": 0.712896953985742, "grad_norm": 0.3563465165177732, "learning_rate": 1.1565190829924838e-06, "loss": 0.1362, "step": 2200 }, { "epoch": 0.7161373946856773, "grad_norm": 0.33363782347377735, "learning_rate": 1.13275422266539e-06, "loss": 0.1398, "step": 2210 }, { "epoch": 0.7193778353856124, "grad_norm": 0.36414316020816895, "learning_rate": 1.109164342955803e-06, "loss": 0.1383, "step": 2220 }, { "epoch": 0.7226182760855476, "grad_norm": 0.36241713354650357, "learning_rate": 1.0857524629052057e-06, "loss": 0.1373, "step": 2230 }, { "epoch": 0.7258587167854829, "grad_norm": 0.35575126832820747, "learning_rate": 1.0625215787746185e-06, "loss": 0.1376, "step": 2240 }, { "epoch": 0.729099157485418, "grad_norm": 0.3581511044472468, "learning_rate": 1.0394746636611364e-06, "loss": 0.1327, "step": 2250 }, { "epoch": 0.7323395981853532, "grad_norm": 0.3487467990800773, "learning_rate": 1.016614667117434e-06, "loss": 0.1362, "step": 2260 }, { "epoch": 0.7355800388852884, "grad_norm": 0.36540009173824517, "learning_rate": 9.939445147742786e-07, "loss": 0.1408, "step": 2270 }, { "epoch": 0.7388204795852236, "grad_norm": 0.3504860844231358, "learning_rate": 9.714671079661048e-07, "loss": 0.1383, "step": 2280 }, { "epoch": 0.7420609202851588, "grad_norm": 0.3546645739584433, "learning_rate": 9.491853233597037e-07, "loss": 0.1367, "step": 2290 }, { "epoch": 0.7453013609850939, "grad_norm": 0.36305507134438186, "learning_rate": 9.271020125860658e-07, "loss": 0.1367, "step": 2300 }, { "epoch": 0.7485418016850292, "grad_norm": 0.3632120141566518, "learning_rate": 9.052200018754276e-07, "loss": 0.1364, "step": 2310 }, { "epoch": 0.7517822423849644, "grad_norm": 0.3222399957976063, "learning_rate": 8.835420916955686e-07, "loss": 0.1376, "step": 2320 }, { "epoch": 0.7550226830848995, "grad_norm": 0.3648037126049122, "learning_rate": 8.620710563934063e-07, "loss": 0.1374, "step": 2330 }, { "epoch": 0.7582631237848347, "grad_norm": 0.38493254190484144, "learning_rate": 8.408096438399371e-07, "loss": 0.1369, "step": 2340 }, { "epoch": 0.76150356448477, "grad_norm": 0.335337634563654, "learning_rate": 8.19760575078562e-07, "loss": 0.1353, "step": 2350 }, { "epoch": 0.7647440051847051, "grad_norm": 0.34948986108995744, "learning_rate": 7.989265439768412e-07, "loss": 0.1336, "step": 2360 }, { "epoch": 0.7679844458846403, "grad_norm": 0.3533447598580161, "learning_rate": 7.783102168817406e-07, "loss": 0.1338, "step": 2370 }, { "epoch": 0.7712248865845756, "grad_norm": 0.35564500184932724, "learning_rate": 7.579142322783837e-07, "loss": 0.1371, "step": 2380 }, { "epoch": 0.7744653272845107, "grad_norm": 0.3565193952902089, "learning_rate": 7.37741200452384e-07, "loss": 0.1333, "step": 2390 }, { "epoch": 0.7777057679844459, "grad_norm": 0.38945562323117644, "learning_rate": 7.177937031557733e-07, "loss": 0.1384, "step": 2400 }, { "epoch": 0.780946208684381, "grad_norm": 0.33188297048475185, "learning_rate": 6.98074293276595e-07, "loss": 0.1304, "step": 2410 }, { "epoch": 0.7841866493843163, "grad_norm": 0.33600376376796814, "learning_rate": 6.785854945121773e-07, "loss": 0.1371, "step": 2420 }, { "epoch": 0.7874270900842515, "grad_norm": 0.3733419224635097, "learning_rate": 6.593298010461541e-07, "loss": 0.1357, "step": 2430 }, { "epoch": 0.7906675307841866, "grad_norm": 0.360994575329127, "learning_rate": 6.403096772292611e-07, "loss": 0.1388, "step": 2440 }, { "epoch": 0.7939079714841218, "grad_norm": 0.3540220491931335, "learning_rate": 6.215275572639387e-07, "loss": 0.1383, "step": 2450 }, { "epoch": 0.7971484121840571, "grad_norm": 0.3421614423791235, "learning_rate": 6.029858448928091e-07, "loss": 0.1374, "step": 2460 }, { "epoch": 0.8003888528839922, "grad_norm": 0.352474503469002, "learning_rate": 5.846869130910413e-07, "loss": 0.1394, "step": 2470 }, { "epoch": 0.8036292935839274, "grad_norm": 0.33788431994154117, "learning_rate": 5.666331037626585e-07, "loss": 0.1345, "step": 2480 }, { "epoch": 0.8068697342838627, "grad_norm": 0.32025075334711434, "learning_rate": 5.488267274408207e-07, "loss": 0.1349, "step": 2490 }, { "epoch": 0.8101101749837978, "grad_norm": 0.36081495813728437, "learning_rate": 5.312700629921181e-07, "loss": 0.1325, "step": 2500 }, { "epoch": 0.813350615683733, "grad_norm": 0.3416845659191573, "learning_rate": 5.139653573249253e-07, "loss": 0.1333, "step": 2510 }, { "epoch": 0.8165910563836681, "grad_norm": 0.3831793796512933, "learning_rate": 4.969148251018385e-07, "loss": 0.1342, "step": 2520 }, { "epoch": 0.8198314970836034, "grad_norm": 0.3578750131718832, "learning_rate": 4.801206484562446e-07, "loss": 0.1352, "step": 2530 }, { "epoch": 0.8230719377835386, "grad_norm": 0.355502152277739, "learning_rate": 4.6358497671304623e-07, "loss": 0.1357, "step": 2540 }, { "epoch": 0.8263123784834737, "grad_norm": 0.3510295514913444, "learning_rate": 4.473099261135977e-07, "loss": 0.1388, "step": 2550 }, { "epoch": 0.829552819183409, "grad_norm": 0.32078925808882724, "learning_rate": 4.312975795448593e-07, "loss": 0.1364, "step": 2560 }, { "epoch": 0.8327932598833442, "grad_norm": 0.3692542497286855, "learning_rate": 4.1554998627283655e-07, "loss": 0.1315, "step": 2570 }, { "epoch": 0.8360337005832793, "grad_norm": 0.37137933087389124, "learning_rate": 4.000691616803076e-07, "loss": 0.1413, "step": 2580 }, { "epoch": 0.8392741412832145, "grad_norm": 0.3882652809375332, "learning_rate": 3.8485708700889913e-07, "loss": 0.1364, "step": 2590 }, { "epoch": 0.8425145819831497, "grad_norm": 0.36297859765424056, "learning_rate": 3.699157091055225e-07, "loss": 0.1346, "step": 2600 }, { "epoch": 0.8457550226830849, "grad_norm": 0.3565105681283779, "learning_rate": 3.552469401732181e-07, "loss": 0.1379, "step": 2610 }, { "epoch": 0.8489954633830201, "grad_norm": 0.33430669724867546, "learning_rate": 3.408526575264298e-07, "loss": 0.1407, "step": 2620 }, { "epoch": 0.8522359040829552, "grad_norm": 0.3705327571148099, "learning_rate": 3.267347033507456e-07, "loss": 0.1341, "step": 2630 }, { "epoch": 0.8554763447828905, "grad_norm": 0.3473212789683562, "learning_rate": 3.128948844671334e-07, "loss": 0.1354, "step": 2640 }, { "epoch": 0.8587167854828257, "grad_norm": 0.35963054694538577, "learning_rate": 2.993349721007041e-07, "loss": 0.136, "step": 2650 }, { "epoch": 0.8619572261827608, "grad_norm": 0.37555057368085243, "learning_rate": 2.860567016540322e-07, "loss": 0.1379, "step": 2660 }, { "epoch": 0.8651976668826961, "grad_norm": 0.38221465588612524, "learning_rate": 2.730617724850523e-07, "loss": 0.138, "step": 2670 }, { "epoch": 0.8684381075826313, "grad_norm": 0.39323307490910586, "learning_rate": 2.603518476895794e-07, "loss": 0.1372, "step": 2680 }, { "epoch": 0.8716785482825664, "grad_norm": 0.32668418769533897, "learning_rate": 2.479285538884649e-07, "loss": 0.1315, "step": 2690 }, { "epoch": 0.8749189889825016, "grad_norm": 0.36967939498979446, "learning_rate": 2.3579348101941817e-07, "loss": 0.1395, "step": 2700 }, { "epoch": 0.8781594296824368, "grad_norm": 0.4148617877855533, "learning_rate": 2.239481821335296e-07, "loss": 0.1346, "step": 2710 }, { "epoch": 0.881399870382372, "grad_norm": 0.3507803299933488, "learning_rate": 2.1239417319650707e-07, "loss": 0.135, "step": 2720 }, { "epoch": 0.8846403110823072, "grad_norm": 0.3431423389326874, "learning_rate": 2.0113293289466484e-07, "loss": 0.1386, "step": 2730 }, { "epoch": 0.8878807517822424, "grad_norm": 0.3556269315719522, "learning_rate": 1.901659024456784e-07, "loss": 0.1374, "step": 2740 }, { "epoch": 0.8911211924821776, "grad_norm": 0.3581655711093919, "learning_rate": 1.7949448541413923e-07, "loss": 0.1349, "step": 2750 }, { "epoch": 0.8943616331821128, "grad_norm": 0.3539219505292951, "learning_rate": 1.6912004753192463e-07, "loss": 0.1372, "step": 2760 }, { "epoch": 0.8976020738820479, "grad_norm": 0.36487534167481467, "learning_rate": 1.5904391652341034e-07, "loss": 0.1398, "step": 2770 }, { "epoch": 0.9008425145819832, "grad_norm": 0.3547252654216283, "learning_rate": 1.492673819355489e-07, "loss": 0.137, "step": 2780 }, { "epoch": 0.9040829552819183, "grad_norm": 0.3624466589823807, "learning_rate": 1.3979169497283369e-07, "loss": 0.1344, "step": 2790 }, { "epoch": 0.9073233959818535, "grad_norm": 0.3597593530124065, "learning_rate": 1.3061806833716773e-07, "loss": 0.1351, "step": 2800 }, { "epoch": 0.9105638366817888, "grad_norm": 0.36978575366992134, "learning_rate": 1.2174767607266214e-07, "loss": 0.1381, "step": 2810 }, { "epoch": 0.9138042773817239, "grad_norm": 0.3394271179919748, "learning_rate": 1.1318165341538096e-07, "loss": 0.1409, "step": 2820 }, { "epoch": 0.9170447180816591, "grad_norm": 0.3886245251582624, "learning_rate": 1.0492109664805572e-07, "loss": 0.1357, "step": 2830 }, { "epoch": 0.9202851587815943, "grad_norm": 0.357080659087376, "learning_rate": 9.69670629597802e-08, "loss": 0.1367, "step": 2840 }, { "epoch": 0.9235255994815295, "grad_norm": 0.3725663246448965, "learning_rate": 8.932057031071113e-08, "loss": 0.1367, "step": 2850 }, { "epoch": 0.9267660401814647, "grad_norm": 0.3534059663914867, "learning_rate": 8.198259730178987e-08, "loss": 0.1372, "step": 2860 }, { "epoch": 0.9300064808813999, "grad_norm": 0.38942343747420805, "learning_rate": 7.495408304950213e-08, "loss": 0.1362, "step": 2870 }, { "epoch": 0.933246921581335, "grad_norm": 0.3482911345014878, "learning_rate": 6.823592706568738e-08, "loss": 0.1364, "step": 2880 }, { "epoch": 0.9364873622812703, "grad_norm": 0.3962969062391369, "learning_rate": 6.182898914241897e-08, "loss": 0.1397, "step": 2890 }, { "epoch": 0.9397278029812054, "grad_norm": 0.3486632243006723, "learning_rate": 5.5734089241969434e-08, "loss": 0.1355, "step": 2900 }, { "epoch": 0.9429682436811406, "grad_norm": 0.3414359245355013, "learning_rate": 4.995200739186967e-08, "loss": 0.1353, "step": 2910 }, { "epoch": 0.9462086843810759, "grad_norm": 0.3577826479652381, "learning_rate": 4.448348358508187e-08, "loss": 0.1349, "step": 2920 }, { "epoch": 0.949449125081011, "grad_norm": 0.39657239893518126, "learning_rate": 3.932921768529413e-08, "loss": 0.1391, "step": 2930 }, { "epoch": 0.9526895657809462, "grad_norm": 0.34868268785953926, "learning_rate": 3.448986933735299e-08, "loss": 0.1408, "step": 2940 }, { "epoch": 0.9559300064808814, "grad_norm": 0.37214717947029213, "learning_rate": 2.996605788283924e-08, "loss": 0.1376, "step": 2950 }, { "epoch": 0.9591704471808166, "grad_norm": 0.37280976502774077, "learning_rate": 2.5758362280807192e-08, "loss": 0.1323, "step": 2960 }, { "epoch": 0.9624108878807518, "grad_norm": 0.3529393622845644, "learning_rate": 2.1867321033687827e-08, "loss": 0.1349, "step": 2970 }, { "epoch": 0.9656513285806869, "grad_norm": 0.344394233275576, "learning_rate": 1.8293432118371146e-08, "loss": 0.1358, "step": 2980 }, { "epoch": 0.9688917692806222, "grad_norm": 0.3857968624258438, "learning_rate": 1.5037152922475207e-08, "loss": 0.1406, "step": 2990 }, { "epoch": 0.9721322099805574, "grad_norm": 0.37594692090340304, "learning_rate": 1.2098900185808781e-08, "loss": 0.1362, "step": 3000 }, { "epoch": 0.9753726506804925, "grad_norm": 0.345262397252086, "learning_rate": 9.479049947038743e-09, "loss": 0.1355, "step": 3010 }, { "epoch": 0.9786130913804277, "grad_norm": 0.39601712390863364, "learning_rate": 7.177937495561616e-09, "loss": 0.134, "step": 3020 }, { "epoch": 0.981853532080363, "grad_norm": 0.3544450146581611, "learning_rate": 5.1958573285959546e-09, "loss": 0.1367, "step": 3030 }, { "epoch": 0.9850939727802981, "grad_norm": 0.36321038651711207, "learning_rate": 3.533063113490276e-09, "loss": 0.1353, "step": 3040 }, { "epoch": 0.9883344134802333, "grad_norm": 0.34666506280478593, "learning_rate": 2.189767655259578e-09, "loss": 0.132, "step": 3050 }, { "epoch": 0.9915748541801686, "grad_norm": 0.34052736841522746, "learning_rate": 1.1661428693512944e-09, "loss": 0.1306, "step": 3060 }, { "epoch": 0.9948152948801037, "grad_norm": 0.31547647192990236, "learning_rate": 4.623197596417828e-10, "loss": 0.1314, "step": 3070 }, { "epoch": 0.9980557355800389, "grad_norm": 0.3819807577926737, "learning_rate": 7.838840167168071e-11, "loss": 0.1368, "step": 3080 }, { "epoch": 1.0, "step": 3086, "total_flos": 190452489388032.0, "train_loss": 0.15608682801641588, "train_runtime": 8265.837, "train_samples_per_second": 47.787, "train_steps_per_second": 0.373 } ], "logging_steps": 10, "max_steps": 3086, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 190452489388032.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }