{
  "best_metric": 0.042311783879995346,
  "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_full_eng/checkpoint-1539",
  "epoch": 2.996902520498026,
  "eval_steps": 171,
  "global_step": 1542,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019435165502581234,
      "grad_norm": 0.2028260976076126,
      "learning_rate": 3.205128205128205e-06,
      "loss": 0.0883,
      "step": 10
    },
    {
      "epoch": 0.03887033100516247,
      "grad_norm": 0.16199472546577454,
      "learning_rate": 6.41025641025641e-06,
      "loss": 0.0862,
      "step": 20
    },
    {
      "epoch": 0.0583054965077437,
      "grad_norm": 0.10014229267835617,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.0785,
      "step": 30
    },
    {
      "epoch": 0.07774066201032494,
      "grad_norm": 0.07943801581859589,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.0772,
      "step": 40
    },
    {
      "epoch": 0.09717582751290617,
      "grad_norm": 0.11369317024946213,
      "learning_rate": 1.602564102564103e-05,
      "loss": 0.0649,
      "step": 50
    },
    {
      "epoch": 0.1166109930154874,
      "grad_norm": 0.10264527052640915,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.0686,
      "step": 60
    },
    {
      "epoch": 0.13604615851806864,
      "grad_norm": 0.08583803474903107,
      "learning_rate": 2.2435897435897437e-05,
      "loss": 0.0657,
      "step": 70
    },
    {
      "epoch": 0.15548132402064987,
      "grad_norm": 0.09326862543821335,
      "learning_rate": 2.4999884878368972e-05,
      "loss": 0.0605,
      "step": 80
    },
    {
      "epoch": 0.1749164895232311,
      "grad_norm": 0.09622487425804138,
      "learning_rate": 2.4995855843928913e-05,
      "loss": 0.0617,
      "step": 90
    },
    {
      "epoch": 0.19435165502581234,
      "grad_norm": 0.10855123400688171,
      "learning_rate": 2.4986072848240374e-05,
      "loss": 0.0548,
      "step": 100
    },
    {
      "epoch": 0.21378682052839357,
      "grad_norm": 0.12510105967521667,
      "learning_rate": 2.4970540396075083e-05,
      "loss": 0.0545,
      "step": 110
    },
    {
      "epoch": 0.2332219860309748,
      "grad_norm": 0.11628145724534988,
      "learning_rate": 2.494926563965445e-05,
      "loss": 0.0601,
      "step": 120
    },
    {
      "epoch": 0.252657151533556,
      "grad_norm": 0.12050613015890121,
      "learning_rate": 2.4922258375356232e-05,
      "loss": 0.0585,
      "step": 130
    },
    {
      "epoch": 0.2720923170361373,
      "grad_norm": 0.08949285745620728,
      "learning_rate": 2.488953103920354e-05,
      "loss": 0.0477,
      "step": 140
    },
    {
      "epoch": 0.2915274825387185,
      "grad_norm": 0.14706853032112122,
      "learning_rate": 2.4851098701138466e-05,
      "loss": 0.0555,
      "step": 150
    },
    {
      "epoch": 0.31096264804129975,
      "grad_norm": 0.13029147684574127,
      "learning_rate": 2.4806979058082832e-05,
      "loss": 0.0493,
      "step": 160
    },
    {
      "epoch": 0.330397813543881,
      "grad_norm": 0.1321103274822235,
      "learning_rate": 2.475719242578929e-05,
      "loss": 0.0547,
      "step": 170
    },
    {
      "epoch": 0.3323413300941391,
      "eval_loss": 0.054034121334552765,
      "eval_runtime": 172.2024,
      "eval_samples_per_second": 5.029,
      "eval_steps_per_second": 5.029,
      "step": 171
    },
    {
      "epoch": 0.3498329790464622,
      "grad_norm": 0.14103983342647552,
      "learning_rate": 2.470176172948652e-05,
      "loss": 0.0522,
      "step": 180
    },
    {
      "epoch": 0.36926814454904344,
      "grad_norm": 0.14120739698410034,
      "learning_rate": 2.4640712493322894e-05,
      "loss": 0.0501,
      "step": 190
    },
    {
      "epoch": 0.3887033100516247,
      "grad_norm": 0.1301490068435669,
      "learning_rate": 2.4574072828613354e-05,
      "loss": 0.0492,
      "step": 200
    },
    {
      "epoch": 0.4081384755542059,
      "grad_norm": 0.1606156975030899,
      "learning_rate": 2.450187342089502e-05,
      "loss": 0.0488,
      "step": 210
    },
    {
      "epoch": 0.42757364105678713,
      "grad_norm": 0.1623048037290573,
      "learning_rate": 2.442414751579744e-05,
      "loss": 0.0459,
      "step": 220
    },
    {
      "epoch": 0.44700880655936837,
      "grad_norm": 0.1424696147441864,
      "learning_rate": 2.434093090373396e-05,
      "loss": 0.0441,
      "step": 230
    },
    {
      "epoch": 0.4664439720619496,
      "grad_norm": 0.13980570435523987,
      "learning_rate": 2.4252261903421375e-05,
      "loss": 0.0483,
      "step": 240
    },
    {
      "epoch": 0.4858791375645308,
      "grad_norm": 0.17693087458610535,
      "learning_rate": 2.415818134423528e-05,
      "loss": 0.0451,
      "step": 250
    },
    {
      "epoch": 0.505314303067112,
      "grad_norm": 0.18210634589195251,
      "learning_rate": 2.405873254740942e-05,
      "loss": 0.0466,
      "step": 260
    },
    {
      "epoch": 0.5247494685696933,
      "grad_norm": 0.1527709811925888,
      "learning_rate": 2.395396130608756e-05,
      "loss": 0.0488,
      "step": 270
    },
    {
      "epoch": 0.5441846340722746,
      "grad_norm": 0.15795762836933136,
      "learning_rate": 2.3843915864237143e-05,
      "loss": 0.0448,
      "step": 280
    },
    {
      "epoch": 0.5636197995748558,
      "grad_norm": 0.15495383739471436,
      "learning_rate": 2.3728646894434413e-05,
      "loss": 0.047,
      "step": 290
    },
    {
      "epoch": 0.583054965077437,
      "grad_norm": 0.17630279064178467,
      "learning_rate": 2.3608207474531236e-05,
      "loss": 0.0429,
      "step": 300
    },
    {
      "epoch": 0.6024901305800182,
      "grad_norm": 0.17523537576198578,
      "learning_rate": 2.3482653063214356e-05,
      "loss": 0.0473,
      "step": 310
    },
    {
      "epoch": 0.6219252960825995,
      "grad_norm": 0.1995943933725357,
      "learning_rate": 2.3352041474468373e-05,
      "loss": 0.0392,
      "step": 320
    },
    {
      "epoch": 0.6413604615851807,
      "grad_norm": 0.1683543622493744,
      "learning_rate": 2.3216432850954155e-05,
      "loss": 0.0438,
      "step": 330
    },
    {
      "epoch": 0.660795627087762,
      "grad_norm": 0.1374560445547104,
      "learning_rate": 2.307588963631497e-05,
      "loss": 0.0388,
      "step": 340
    },
    {
      "epoch": 0.6646826601882782,
      "eval_loss": 0.048522137105464935,
      "eval_runtime": 174.8794,
      "eval_samples_per_second": 4.952,
      "eval_steps_per_second": 4.952,
      "step": 342
    },
    {
      "epoch": 0.6802307925903431,
      "grad_norm": 0.166055366396904,
      "learning_rate": 2.293047654642309e-05,
      "loss": 0.0469,
      "step": 350
    },
    {
      "epoch": 0.6996659580929244,
      "grad_norm": 0.14119000732898712,
      "learning_rate": 2.2780260539580116e-05,
      "loss": 0.0424,
      "step": 360
    },
    {
      "epoch": 0.7191011235955056,
      "grad_norm": 0.23057888448238373,
      "learning_rate": 2.2625310785684688e-05,
      "loss": 0.0451,
      "step": 370
    },
    {
      "epoch": 0.7385362890980869,
      "grad_norm": 0.1304253786802292,
      "learning_rate": 2.2465698634381892e-05,
      "loss": 0.0434,
      "step": 380
    },
    {
      "epoch": 0.7579714546006681,
      "grad_norm": 0.17952455580234528,
      "learning_rate": 2.2301497582208884e-05,
      "loss": 0.0409,
      "step": 390
    },
    {
      "epoch": 0.7774066201032493,
      "grad_norm": 0.15560920536518097,
      "learning_rate": 2.2132783238751987e-05,
      "loss": 0.0465,
      "step": 400
    },
    {
      "epoch": 0.7968417856058305,
      "grad_norm": 0.12066332250833511,
      "learning_rate": 2.1959633291830785e-05,
      "loss": 0.0433,
      "step": 410
    },
    {
      "epoch": 0.8162769511084118,
      "grad_norm": 0.15932129323482513,
      "learning_rate": 2.1782127471725232e-05,
      "loss": 0.0458,
      "step": 420
    },
    {
      "epoch": 0.835712116610993,
      "grad_norm": 0.19025273621082306,
      "learning_rate": 2.160034751446231e-05,
      "loss": 0.0522,
      "step": 430
    },
    {
      "epoch": 0.8551472821135743,
      "grad_norm": 0.15156866610050201,
      "learning_rate": 2.1414377124179038e-05,
      "loss": 0.0433,
      "step": 440
    },
    {
      "epoch": 0.8745824476161554,
      "grad_norm": 0.1594618409872055,
      "learning_rate": 2.1224301934579293e-05,
      "loss": 0.0434,
      "step": 450
    },
    {
      "epoch": 0.8940176131187367,
      "grad_norm": 0.16077858209609985,
      "learning_rate": 2.1030209469502098e-05,
      "loss": 0.0426,
      "step": 460
    },
    {
      "epoch": 0.9134527786213179,
      "grad_norm": 0.15807421505451202,
      "learning_rate": 2.0832189102619543e-05,
      "loss": 0.0461,
      "step": 470
    },
    {
      "epoch": 0.9328879441238992,
      "grad_norm": 0.20585452020168304,
      "learning_rate": 2.0630332016282927e-05,
      "loss": 0.0429,
      "step": 480
    },
    {
      "epoch": 0.9523231096264804,
      "grad_norm": 0.1859339326620102,
      "learning_rate": 2.0424731159536083e-05,
      "loss": 0.0432,
      "step": 490
    },
    {
      "epoch": 0.9717582751290617,
      "grad_norm": 0.20674780011177063,
      "learning_rate": 2.021548120531516e-05,
      "loss": 0.0392,
      "step": 500
    },
    {
      "epoch": 0.9911934406316428,
      "grad_norm": 0.22314420342445374,
      "learning_rate": 2.0002678506854606e-05,
      "loss": 0.041,
      "step": 510
    },
    {
      "epoch": 0.9970239902824173,
      "eval_loss": 0.04610577970743179,
      "eval_runtime": 175.1913,
      "eval_samples_per_second": 4.943,
      "eval_steps_per_second": 4.943,
      "step": 513
    },
    {
      "epoch": 1.010628606134224,
      "grad_norm": 0.1707136183977127,
      "learning_rate": 1.9786421053319455e-05,
      "loss": 0.0468,
      "step": 520
    },
    {
      "epoch": 1.0300637716368053,
      "grad_norm": 0.18121393024921417,
      "learning_rate": 1.9566808424684284e-05,
      "loss": 0.0361,
      "step": 530
    },
    {
      "epoch": 1.0494989371393866,
      "grad_norm": 0.17815589904785156,
      "learning_rate": 1.9343941745879695e-05,
      "loss": 0.0418,
      "step": 540
    },
    {
      "epoch": 1.0689341026419679,
      "grad_norm": 0.17634443938732147,
      "learning_rate": 1.9117923640227314e-05,
      "loss": 0.0437,
      "step": 550
    },
    {
      "epoch": 1.088369268144549,
      "grad_norm": 0.18102432787418365,
      "learning_rate": 1.8888858182184925e-05,
      "loss": 0.0426,
      "step": 560
    },
    {
      "epoch": 1.1078044336471302,
      "grad_norm": 0.20596696436405182,
      "learning_rate": 1.865685084942331e-05,
      "loss": 0.0414,
      "step": 570
    },
    {
      "epoch": 1.1272395991497115,
      "grad_norm": 0.2145373523235321,
      "learning_rate": 1.8422008474257013e-05,
      "loss": 0.0354,
      "step": 580
    },
    {
      "epoch": 1.1466747646522928,
      "grad_norm": 0.2385258674621582,
      "learning_rate": 1.8184439194451326e-05,
      "loss": 0.0357,
      "step": 590
    },
    {
      "epoch": 1.166109930154874,
      "grad_norm": 0.23679479956626892,
      "learning_rate": 1.7944252403428097e-05,
      "loss": 0.041,
      "step": 600
    },
    {
      "epoch": 1.1855450956574551,
      "grad_norm": 0.1947854906320572,
      "learning_rate": 1.770155869989343e-05,
      "loss": 0.0407,
      "step": 610
    },
    {
      "epoch": 1.2049802611600364,
      "grad_norm": 0.25392264127731323,
      "learning_rate": 1.7456469836910334e-05,
      "loss": 0.0405,
      "step": 620
    },
    {
      "epoch": 1.2244154266626177,
      "grad_norm": 0.2636931240558624,
      "learning_rate": 1.7209098670439817e-05,
      "loss": 0.0442,
      "step": 630
    },
    {
      "epoch": 1.243850592165199,
      "grad_norm": 0.19380666315555573,
      "learning_rate": 1.695955910737419e-05,
      "loss": 0.0344,
      "step": 640
    },
    {
      "epoch": 1.26328575766778,
      "grad_norm": 0.2423335164785385,
      "learning_rate": 1.670796605308638e-05,
      "loss": 0.0415,
      "step": 650
    },
    {
      "epoch": 1.2827209231703613,
      "grad_norm": 0.20322546362876892,
      "learning_rate": 1.6454435358519524e-05,
      "loss": 0.0381,
      "step": 660
    },
    {
      "epoch": 1.3021560886729426,
      "grad_norm": 0.20570382475852966,
      "learning_rate": 1.6199083766841115e-05,
      "loss": 0.035,
      "step": 670
    },
    {
      "epoch": 1.321591254175524,
      "grad_norm": 0.23237545788288116,
      "learning_rate": 1.594202885968636e-05,
      "loss": 0.0447,
      "step": 680
    },
    {
      "epoch": 1.3293653203765563,
      "eval_loss": 0.0446239709854126,
      "eval_runtime": 174.4977,
      "eval_samples_per_second": 4.963,
      "eval_steps_per_second": 4.963,
      "step": 684
    },
    {
      "epoch": 1.341026419678105,
      "grad_norm": 0.2273474782705307,
      "learning_rate": 1.568338900301536e-05,
      "loss": 0.0406,
      "step": 690
    },
    {
      "epoch": 1.3604615851806863,
      "grad_norm": 0.2105632871389389,
      "learning_rate": 1.5423283292609255e-05,
      "loss": 0.0384,
      "step": 700
    },
    {
      "epoch": 1.3798967506832676,
      "grad_norm": 0.728905200958252,
      "learning_rate": 1.5161831499230197e-05,
      "loss": 0.0385,
      "step": 710
    },
    {
      "epoch": 1.3993319161858488,
      "grad_norm": 0.2697829604148865,
      "learning_rate": 1.4899154013470574e-05,
      "loss": 0.0407,
      "step": 720
    },
    {
      "epoch": 1.4187670816884301,
      "grad_norm": 0.23418137431144714,
      "learning_rate": 1.4635371790316805e-05,
      "loss": 0.0425,
      "step": 730
    },
    {
      "epoch": 1.4382022471910112,
      "grad_norm": 0.21163399517536163,
      "learning_rate": 1.437060629345325e-05,
      "loss": 0.0369,
      "step": 740
    },
    {
      "epoch": 1.4576374126935925,
      "grad_norm": 0.24824394285678864,
      "learning_rate": 1.4104979439331889e-05,
      "loss": 0.0413,
      "step": 750
    },
    {
      "epoch": 1.4770725781961738,
      "grad_norm": 0.24107202887535095,
      "learning_rate": 1.383861354103349e-05,
      "loss": 0.0368,
      "step": 760
    },
    {
      "epoch": 1.4965077436987548,
      "grad_norm": 0.25261572003364563,
      "learning_rate": 1.357163125194618e-05,
      "loss": 0.0437,
      "step": 770
    },
    {
      "epoch": 1.5159429092013361,
      "grad_norm": 0.1909024715423584,
      "learning_rate": 1.3304155509287273e-05,
      "loss": 0.0376,
      "step": 780
    },
    {
      "epoch": 1.5353780747039174,
      "grad_norm": 0.24820125102996826,
      "learning_rate": 1.3036309477494433e-05,
      "loss": 0.038,
      "step": 790
    },
    {
      "epoch": 1.5548132402064985,
      "grad_norm": 0.2151060849428177,
      "learning_rate": 1.27682164915122e-05,
      "loss": 0.0427,
      "step": 800
    },
    {
      "epoch": 1.57424840570908,
      "grad_norm": 0.2735498249530792,
      "learning_rate": 1.25e-05,
      "loss": 0.0405,
      "step": 810
    },
    {
      "epoch": 1.593683571211661,
      "grad_norm": 0.20167022943496704,
      "learning_rate": 1.2231783508487806e-05,
      "loss": 0.0361,
      "step": 820
    },
    {
      "epoch": 1.6131187367142423,
      "grad_norm": 0.29892289638519287,
      "learning_rate": 1.1963690522505568e-05,
      "loss": 0.0343,
      "step": 830
    },
    {
      "epoch": 1.6325539022168236,
      "grad_norm": 0.2181161344051361,
      "learning_rate": 1.169584449071273e-05,
      "loss": 0.044,
      "step": 840
    },
    {
      "epoch": 1.6519890677194047,
      "grad_norm": 0.24029949307441711,
      "learning_rate": 1.142836874805382e-05,
      "loss": 0.0347,
      "step": 850
    },
    {
      "epoch": 1.6617066504706954,
      "eval_loss": 0.04329855740070343,
      "eval_runtime": 170.3718,
      "eval_samples_per_second": 5.083,
      "eval_steps_per_second": 5.083,
      "step": 855
    },
    {
      "epoch": 1.6714242332219862,
      "grad_norm": 0.23985505104064941,
      "learning_rate": 1.1161386458966511e-05,
      "loss": 0.0401,
      "step": 860
    },
    {
      "epoch": 1.6908593987245673,
      "grad_norm": 0.22673290967941284,
      "learning_rate": 1.0895020560668112e-05,
      "loss": 0.0364,
      "step": 870
    },
    {
      "epoch": 1.7102945642271485,
      "grad_norm": 0.22750601172447205,
      "learning_rate": 1.0629393706546752e-05,
      "loss": 0.039,
      "step": 880
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.24846433103084564,
      "learning_rate": 1.03646282096832e-05,
      "loss": 0.0341,
      "step": 890
    },
    {
      "epoch": 1.749164895232311,
      "grad_norm": 0.19867610931396484,
      "learning_rate": 1.0100845986529429e-05,
      "loss": 0.036,
      "step": 900
    },
    {
      "epoch": 1.7686000607348922,
      "grad_norm": 0.2108948975801468,
      "learning_rate": 9.838168500769806e-06,
      "loss": 0.0359,
      "step": 910
    },
    {
      "epoch": 1.7880352262374735,
      "grad_norm": 0.22352129220962524,
      "learning_rate": 9.576716707390745e-06,
      "loss": 0.0432,
      "step": 920
    },
    {
      "epoch": 1.8074703917400545,
      "grad_norm": 0.2634281516075134,
      "learning_rate": 9.316610996984642e-06,
      "loss": 0.0371,
      "step": 930
    },
    {
      "epoch": 1.826905557242636,
      "grad_norm": 0.261662095785141,
      "learning_rate": 9.057971140313645e-06,
      "loss": 0.0414,
      "step": 940
    },
    {
      "epoch": 1.846340722745217,
      "grad_norm": 0.269505113363266,
      "learning_rate": 8.800916233158885e-06,
      "loss": 0.033,
      "step": 950
    },
    {
      "epoch": 1.8657758882477984,
      "grad_norm": 0.2583780288696289,
      "learning_rate": 8.545564641480484e-06,
      "loss": 0.04,
      "step": 960
    },
    {
      "epoch": 1.8852110537503797,
      "grad_norm": 0.2607627213001251,
      "learning_rate": 8.292033946913624e-06,
      "loss": 0.0354,
      "step": 970
    },
    {
      "epoch": 1.9046462192529607,
      "grad_norm": 0.23419621586799622,
      "learning_rate": 8.040440892625817e-06,
      "loss": 0.0362,
      "step": 980
    },
    {
      "epoch": 1.924081384755542,
      "grad_norm": 0.2785259783267975,
      "learning_rate": 7.790901329560186e-06,
      "loss": 0.0367,
      "step": 990
    },
    {
      "epoch": 1.9435165502581233,
      "grad_norm": 0.2678421437740326,
      "learning_rate": 7.543530163089671e-06,
      "loss": 0.0363,
      "step": 1000
    },
    {
      "epoch": 1.9629517157607044,
      "grad_norm": 0.2274320125579834,
      "learning_rate": 7.29844130010657e-06,
      "loss": 0.0395,
      "step": 1010
    },
    {
      "epoch": 1.9823868812632859,
      "grad_norm": 0.2792135179042816,
      "learning_rate": 7.055747596571904e-06,
      "loss": 0.0374,
      "step": 1020
    },
    {
      "epoch": 1.9940479805648343,
      "eval_loss": 0.04268278926610947,
      "eval_runtime": 169.855,
      "eval_samples_per_second": 5.098,
      "eval_steps_per_second": 5.098,
      "step": 1026
    },
    {
      "epoch": 2.001822046765867,
      "grad_norm": 0.2434389591217041,
      "learning_rate": 6.815560805548682e-06,
      "loss": 0.0359,
      "step": 1030
    },
    {
      "epoch": 2.021257212268448,
      "grad_norm": 0.2474217265844345,
      "learning_rate": 6.577991525742991e-06,
      "loss": 0.0301,
      "step": 1040
    },
    {
      "epoch": 2.0406923777710295,
      "grad_norm": 0.21972987055778503,
      "learning_rate": 6.3431491505766965e-06,
      "loss": 0.031,
      "step": 1050
    },
    {
      "epoch": 2.0601275432736106,
      "grad_norm": 0.26206907629966736,
      "learning_rate": 6.111141817815079e-06,
      "loss": 0.0367,
      "step": 1060
    },
    {
      "epoch": 2.079562708776192,
      "grad_norm": 0.26828330755233765,
      "learning_rate": 5.882076359772686e-06,
      "loss": 0.0358,
      "step": 1070
    },
    {
      "epoch": 2.098997874278773,
      "grad_norm": 0.3341256380081177,
      "learning_rate": 5.656058254120305e-06,
      "loss": 0.0362,
      "step": 1080
    },
    {
      "epoch": 2.118433039781354,
      "grad_norm": 0.24040237069129944,
      "learning_rate": 5.4331915753157175e-06,
      "loss": 0.0336,
      "step": 1090
    },
    {
      "epoch": 2.1378682052839357,
      "grad_norm": 0.2951533794403076,
      "learning_rate": 5.213578946680547e-06,
      "loss": 0.0374,
      "step": 1100
    },
    {
      "epoch": 2.157303370786517,
      "grad_norm": 0.3339778184890747,
      "learning_rate": 4.997321493145399e-06,
      "loss": 0.0336,
      "step": 1110
    },
    {
      "epoch": 2.176738536289098,
      "grad_norm": 0.28566041588783264,
      "learning_rate": 4.784518794684843e-06,
      "loss": 0.0305,
      "step": 1120
    },
    {
      "epoch": 2.1961737017916794,
      "grad_norm": 0.23707829415798187,
      "learning_rate": 4.575268840463919e-06,
      "loss": 0.0347,
      "step": 1130
    },
    {
      "epoch": 2.2156088672942604,
      "grad_norm": 0.268509179353714,
      "learning_rate": 4.3696679837170755e-06,
      "loss": 0.0338,
      "step": 1140
    },
    {
      "epoch": 2.235044032796842,
      "grad_norm": 0.2489359974861145,
      "learning_rate": 4.16781089738046e-06,
      "loss": 0.0346,
      "step": 1150
    },
    {
      "epoch": 2.254479198299423,
      "grad_norm": 0.2973306179046631,
      "learning_rate": 3.969790530497904e-06,
      "loss": 0.0341,
      "step": 1160
    },
    {
      "epoch": 2.273914363802004,
      "grad_norm": 0.2385181337594986,
      "learning_rate": 3.7756980654207032e-06,
      "loss": 0.0307,
      "step": 1170
    },
    {
      "epoch": 2.2933495293045856,
      "grad_norm": 0.24831977486610413,
      "learning_rate": 3.585622875820965e-06,
      "loss": 0.0324,
      "step": 1180
    },
    {
      "epoch": 2.3127846948071666,
      "grad_norm": 0.2952122092247009,
      "learning_rate": 3.399652485537691e-06,
      "loss": 0.0337,
      "step": 1190
    },
    {
      "epoch": 2.3263893106589735,
      "eval_loss": 0.042657386511564255,
      "eval_runtime": 168.8317,
      "eval_samples_per_second": 5.129,
      "eval_steps_per_second": 5.129,
      "step": 1197
    },
    {
      "epoch": 2.332219860309748,
      "grad_norm": 0.29106399416923523,
      "learning_rate": 3.2178725282747665e-06,
      "loss": 0.0346,
      "step": 1200
    },
    {
      "epoch": 2.351655025812329,
      "grad_norm": 0.30523982644081116,
      "learning_rate": 3.040366708169222e-06,
      "loss": 0.036,
      "step": 1210
    },
    {
      "epoch": 2.3710901913149103,
      "grad_norm": 0.2523854672908783,
      "learning_rate": 2.8672167612480163e-06,
      "loss": 0.0298,
      "step": 1220
    },
    {
      "epoch": 2.390525356817492,
      "grad_norm": 0.2531813383102417,
      "learning_rate": 2.698502417791121e-06,
      "loss": 0.0383,
      "step": 1230
    },
    {
      "epoch": 2.409960522320073,
      "grad_norm": 0.2635211944580078,
      "learning_rate": 2.534301365618107e-06,
      "loss": 0.0357,
      "step": 1240
    },
    {
      "epoch": 2.4293956878226544,
      "grad_norm": 0.26689672470092773,
      "learning_rate": 2.374689214315311e-06,
      "loss": 0.0333,
      "step": 1250
    },
    {
      "epoch": 2.4488308533252354,
      "grad_norm": 0.29953232407569885,
      "learning_rate": 2.2197394604198853e-06,
      "loss": 0.0317,
      "step": 1260
    },
    {
      "epoch": 2.4682660188278165,
      "grad_norm": 0.21628761291503906,
      "learning_rate": 2.069523453576909e-06,
      "loss": 0.0362,
      "step": 1270
    },
    {
      "epoch": 2.487701184330398,
      "grad_norm": 0.2457425892353058,
      "learning_rate": 1.924110363685033e-06,
      "loss": 0.0353,
      "step": 1280
    },
    {
      "epoch": 2.507136349832979,
      "grad_norm": 0.3192308247089386,
      "learning_rate": 1.783567149045845e-06,
      "loss": 0.036,
      "step": 1290
    },
    {
      "epoch": 2.52657151533556,
      "grad_norm": 0.2815244793891907,
      "learning_rate": 1.6479585255316287e-06,
      "loss": 0.0329,
      "step": 1300
    },
    {
      "epoch": 2.5460066808381416,
      "grad_norm": 0.2549531161785126,
      "learning_rate": 1.5173469367856477e-06,
      "loss": 0.0382,
      "step": 1310
    },
    {
      "epoch": 2.5654418463407227,
      "grad_norm": 0.25880110263824463,
      "learning_rate": 1.3917925254687686e-06,
      "loss": 0.0344,
      "step": 1320
    },
    {
      "epoch": 2.5848770118433038,
      "grad_norm": 0.22720050811767578,
      "learning_rate": 1.271353105565591e-06,
      "loss": 0.0353,
      "step": 1330
    },
    {
      "epoch": 2.6043121773458853,
      "grad_norm": 0.2991912364959717,
      "learning_rate": 1.1560841357628582e-06,
      "loss": 0.0369,
      "step": 1340
    },
    {
      "epoch": 2.6237473428484663,
      "grad_norm": 0.3291521668434143,
      "learning_rate": 1.046038693912442e-06,
      "loss": 0.0331,
      "step": 1350
    },
    {
      "epoch": 2.643182508351048,
      "grad_norm": 0.24359193444252014,
      "learning_rate": 9.412674525905815e-07,
      "loss": 0.0335,
      "step": 1360
    },
    {
      "epoch": 2.6587306407531126,
      "eval_loss": 0.042365700006484985,
      "eval_runtime": 168.4092,
      "eval_samples_per_second": 5.142,
      "eval_steps_per_second": 5.142,
      "step": 1368
    },
    {
      "epoch": 2.662617673853629,
      "grad_norm": 0.30196014046669006,
      "learning_rate": 8.4181865576472e-07,
      "loss": 0.0319,
      "step": 1370
    },
    {
      "epoch": 2.68205283935621,
      "grad_norm": 0.31683069467544556,
      "learning_rate": 7.477380965786263e-07,
      "loss": 0.0353,
      "step": 1380
    },
    {
      "epoch": 2.7014880048587915,
      "grad_norm": 0.24554206430912018,
      "learning_rate": 6.590690962660393e-07,
      "loss": 0.0349,
      "step": 1390
    },
    {
      "epoch": 2.7209231703613725,
      "grad_norm": 0.3739015460014343,
      "learning_rate": 5.758524842025631e-07,
      "loss": 0.0353,
      "step": 1400
    },
    {
      "epoch": 2.740358335863954,
      "grad_norm": 0.27808961272239685,
      "learning_rate": 4.98126579104978e-07,
      "loss": 0.0337,
      "step": 1410
    },
    {
      "epoch": 2.759793501366535,
      "grad_norm": 0.2409674972295761,
      "learning_rate": 4.259271713866475e-07,
      "loss": 0.0357,
      "step": 1420
    },
    {
      "epoch": 2.779228666869116,
      "grad_norm": 0.2730494737625122,
      "learning_rate": 3.5928750667710844e-07,
      "loss": 0.0339,
      "step": 1430
    },
    {
      "epoch": 2.7986638323716977,
      "grad_norm": 0.23926123976707458,
      "learning_rate": 2.982382705134817e-07,
      "loss": 0.0349,
      "step": 1440
    },
    {
      "epoch": 2.8180989978742788,
      "grad_norm": 0.21703185141086578,
      "learning_rate": 2.4280757421071414e-07,
      "loss": 0.0366,
      "step": 1450
    },
    {
      "epoch": 2.8375341633768603,
      "grad_norm": 0.2484457939863205,
      "learning_rate": 1.9302094191716856e-07,
      "loss": 0.0338,
      "step": 1460
    },
    {
      "epoch": 2.8569693288794413,
      "grad_norm": 0.30563613772392273,
      "learning_rate": 1.489012988615368e-07,
      "loss": 0.0346,
      "step": 1470
    },
    {
      "epoch": 2.8764044943820224,
      "grad_norm": 0.3028404414653778,
      "learning_rate": 1.104689607964643e-07,
      "loss": 0.0386,
      "step": 1480
    },
    {
      "epoch": 2.8958396598846035,
      "grad_norm": 0.3035370111465454,
      "learning_rate": 7.774162464377066e-08,
      "loss": 0.0375,
      "step": 1490
    },
    {
      "epoch": 2.915274825387185,
      "grad_norm": 0.25364699959754944,
      "learning_rate": 5.073436034554874e-08,
      "loss": 0.0379,
      "step": 1500
    },
    {
      "epoch": 2.934709990889766,
      "grad_norm": 0.2718573212623596,
      "learning_rate": 2.945960392492092e-08,
      "loss": 0.0324,
      "step": 1510
    },
    {
      "epoch": 2.9541451563923475,
      "grad_norm": 0.33609631657600403,
      "learning_rate": 1.3927151759626777e-08,
      "loss": 0.0329,
      "step": 1520
    },
    {
      "epoch": 2.9735803218949286,
      "grad_norm": 0.2513211965560913,
      "learning_rate": 4.144156071086979e-09,
      "loss": 0.0338,
      "step": 1530
    },
    {
      "epoch": 2.9910719708472517,
      "eval_loss": 0.042311783879995346,
      "eval_runtime": 168.3509,
      "eval_samples_per_second": 5.144,
      "eval_steps_per_second": 5.144,
      "step": 1539
    },
    {
      "epoch": 2.9930154873975097,
      "grad_norm": 0.2795769274234772,
      "learning_rate": 1.1512163102661566e-10,
      "loss": 0.0348,
      "step": 1540
    },
    {
      "epoch": 2.996902520498026,
      "step": 1542,
      "total_flos": 1.1822411081967206e+18,
      "train_loss": 0.04155438780378739,
      "train_runtime": 32863.2543,
      "train_samples_per_second": 1.503,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 10,
  "max_steps": 1542,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 171,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1822411081967206e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}