{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996011396011396,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 7.721771118166202,
      "learning_rate": 7.575757575757576e-07,
      "loss": 0.8289,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 2.2196723074771856,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.7833,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.0697085967257374,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7258,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.946378685187564,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.7109,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.884291407059407,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.7009,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.8430409247766276,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6764,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.7095666221058156,
      "learning_rate": 4.999885938412857e-06,
      "loss": 0.6695,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.7722552802639886,
      "learning_rate": 4.998602878364678e-06,
      "loss": 0.668,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.5199828224041042,
      "learning_rate": 4.995894997002464e-06,
      "loss": 0.6481,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.35947482551248233,
      "learning_rate": 4.991764010168139e-06,
      "loss": 0.6463,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.35190376887433095,
      "learning_rate": 4.986212535450668e-06,
      "loss": 0.6363,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.32163538115561413,
      "learning_rate": 4.979244090527443e-06,
      "loss": 0.6439,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2887214334188296,
      "learning_rate": 4.970863090935304e-06,
      "loss": 0.6446,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.308321908181046,
      "learning_rate": 4.961074847272654e-06,
      "loss": 0.6464,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3331640361465285,
      "learning_rate": 4.949885561834406e-06,
      "loss": 0.6387,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.30443426256256545,
      "learning_rate": 4.9373023246819205e-06,
      "loss": 0.6437,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35206700783272254,
      "learning_rate": 4.923333109150404e-06,
      "loss": 0.6354,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.2984394309063013,
      "learning_rate": 4.907986766796625e-06,
      "loss": 0.6408,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.30146317066036515,
      "learning_rate": 4.891273021790152e-06,
      "loss": 0.6332,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3100071631390779,
      "learning_rate": 4.873202464751653e-06,
      "loss": 0.6412,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.2974627026912829,
      "learning_rate": 4.853786546042184e-06,
      "loss": 0.6374,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.30319530898990127,
      "learning_rate": 4.833037568507691e-06,
      "loss": 0.6411,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3231897844042923,
      "learning_rate": 4.810968679683349e-06,
      "loss": 0.6366,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.3160397388072386,
      "learning_rate": 4.787593863462657e-06,
      "loss": 0.6324,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.32560366569190685,
      "learning_rate": 4.762927931236582e-06,
      "loss": 0.6373,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3102251700233753,
      "learning_rate": 4.736986512508363e-06,
      "loss": 0.6354,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.30630467227124336,
      "learning_rate": 4.7097860449899104e-06,
      "loss": 0.6325,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3186887311486297,
      "learning_rate": 4.681343764186101e-06,
      "loss": 0.6433,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3133089169723842,
      "learning_rate": 4.651677692473539e-06,
      "loss": 0.632,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.28989683764083396,
      "learning_rate": 4.620806627680728e-06,
      "loss": 0.6299,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2982956286376421,
      "learning_rate": 4.588750131176874e-06,
      "loss": 0.6298,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.30957031022341586,
      "learning_rate": 4.555528515476878e-06,
      "loss": 0.6303,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.2891857200549788,
      "learning_rate": 4.521162831370363e-06,
      "loss": 0.627,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3021616168579128,
      "learning_rate": 4.485674854582895e-06,
      "loss": 0.6328,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.31483288715826147,
      "learning_rate": 4.449087071977851e-06,
      "loss": 0.6398,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.31632498976054596,
      "learning_rate": 4.411422667307682e-06,
      "loss": 0.6315,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.316841155044236,
      "learning_rate": 4.372705506523583e-06,
      "loss": 0.6253,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.31884315949707576,
      "learning_rate": 4.3329601226529e-06,
      "loss": 0.6375,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.2973039383787328,
      "learning_rate": 4.2922117002538395e-06,
      "loss": 0.6361,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.303238556973125,
      "learning_rate": 4.25048605945734e-06,
      "loss": 0.6393,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.27331838146217086,
      "learning_rate": 4.207809639606213e-06,
      "loss": 0.6355,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.2953393998494738,
      "learning_rate": 4.164209482501922e-06,
      "loss": 0.6224,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.32451088199651634,
      "learning_rate": 4.1197132152696215e-06,
      "loss": 0.6355,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6260784268379211,
      "eval_runtime": 443.1249,
      "eval_samples_per_second": 26.681,
      "eval_steps_per_second": 0.417,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.306337337448167,
      "learning_rate": 4.074349032852293e-06,
      "loss": 0.6486,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.3316028387472753,
      "learning_rate": 4.028145680145101e-06,
      "loss": 0.6053,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.3354142341443882,
      "learning_rate": 3.981132433781259e-06,
      "loss": 0.5989,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.279678486533018,
      "learning_rate": 3.9333390835809745e-06,
      "loss": 0.5999,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.29032076486517194,
      "learning_rate": 3.8847959136752025e-06,
      "loss": 0.6073,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3085188061272091,
      "learning_rate": 3.835533683316186e-06,
      "loss": 0.6123,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.2768510453588866,
      "learning_rate": 3.7855836073869388e-06,
      "loss": 0.6022,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.30709259944658746,
      "learning_rate": 3.734977336622016e-06,
      "loss": 0.6,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.3017380612287452,
      "learning_rate": 3.683746937552109e-06,
      "loss": 0.6057,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.28406628735280065,
      "learning_rate": 3.631924872185169e-06,
      "loss": 0.5986,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.2966781609925149,
      "learning_rate": 3.579543977436948e-06,
      "loss": 0.6088,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.291240646673183,
      "learning_rate": 3.5266374443239652e-06,
      "loss": 0.6052,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.28836969889482655,
      "learning_rate": 3.473238796932114e-06,
      "loss": 0.6068,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.2924513257201025,
      "learning_rate": 3.419381871174207e-06,
      "loss": 0.6007,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2641557953345735,
      "learning_rate": 3.365100793349943e-06,
      "loss": 0.5991,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.26865681955257537,
      "learning_rate": 3.310429958521862e-06,
      "loss": 0.5991,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.29773422404182115,
      "learning_rate": 3.255404008721009e-06,
      "loss": 0.6045,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.28457189465317867,
      "learning_rate": 3.2000578109961007e-06,
      "loss": 0.6046,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.2870493796752586,
      "learning_rate": 3.1444264353201075e-06,
      "loss": 0.6072,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.27767602096339566,
      "learning_rate": 3.0885451323682624e-06,
      "loss": 0.605,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.2946593650850497,
      "learning_rate": 3.0324493111815605e-06,
      "loss": 0.5998,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.28935219059578415,
      "learning_rate": 2.976174516729914e-06,
      "loss": 0.5976,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.2730683445684682,
      "learning_rate": 2.919756407389174e-06,
      "loss": 0.5975,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.2930286347326111,
      "learning_rate": 2.8632307323462955e-06,
      "loss": 0.605,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.26579456750893116,
      "learning_rate": 2.8066333089469583e-06,
      "loss": 0.5936,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.3230645795384124,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.5975,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.28117111383966903,
      "learning_rate": 2.693366691053043e-06,
      "loss": 0.6131,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.2822222724697645,
      "learning_rate": 2.6367692676537048e-06,
      "loss": 0.6001,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.28867644358152766,
      "learning_rate": 2.5802435926108264e-06,
      "loss": 0.6046,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.2951163516853766,
      "learning_rate": 2.523825483270087e-06,
      "loss": 0.5976,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.2895022079013085,
      "learning_rate": 2.4675506888184407e-06,
      "loss": 0.5986,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.28803561948416817,
      "learning_rate": 2.4114548676317383e-06,
      "loss": 0.5959,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.2811878972368231,
      "learning_rate": 2.355573564679893e-06,
      "loss": 0.6001,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.2961475141311613,
      "learning_rate": 2.2999421890039004e-06,
      "loss": 0.5966,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.2817242594660535,
      "learning_rate": 2.244595991278992e-06,
      "loss": 0.6036,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.2737840531940691,
      "learning_rate": 2.189570041478139e-06,
      "loss": 0.6011,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.2794621872674546,
      "learning_rate": 2.134899206650058e-06,
      "loss": 0.588,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.2927942520392028,
      "learning_rate": 2.0806181288257937e-06,
      "loss": 0.5958,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.27817969838341117,
      "learning_rate": 2.026761203067887e-06,
      "loss": 0.5936,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.27238251100687083,
      "learning_rate": 1.973362555676035e-06,
      "loss": 0.5973,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.28382896114807354,
      "learning_rate": 1.920456022563053e-06,
      "loss": 0.602,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.2890187050893256,
      "learning_rate": 1.8680751278148315e-06,
      "loss": 0.5999,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.2764703203930875,
      "learning_rate": 1.8162530624478918e-06,
      "loss": 0.6011,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.301116268621859,
      "learning_rate": 1.7650226633779838e-06,
      "loss": 0.5987,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6201021671295166,
      "eval_runtime": 444.2714,
      "eval_samples_per_second": 26.612,
      "eval_steps_per_second": 0.416,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.26698763167471024,
      "learning_rate": 1.7144163926130621e-06,
      "loss": 0.6215,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.28025161636752033,
      "learning_rate": 1.6644663166838153e-06,
      "loss": 0.5677,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.29104643957833876,
      "learning_rate": 1.6152040863247986e-06,
      "loss": 0.5834,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.2975645428962194,
      "learning_rate": 1.5666609164190258e-06,
      "loss": 0.5813,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.27536175163113397,
      "learning_rate": 1.5188675662187419e-06,
      "loss": 0.5844,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.2738236952513253,
      "learning_rate": 1.4718543198548998e-06,
      "loss": 0.582,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.28081973540429417,
      "learning_rate": 1.425650967147707e-06,
      "loss": 0.5767,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.27041793718088686,
      "learning_rate": 1.3802867847303786e-06,
      "loss": 0.5776,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.2780771240410971,
      "learning_rate": 1.3357905174980784e-06,
      "loss": 0.5825,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.28042176207992897,
      "learning_rate": 1.292190360393788e-06,
      "loss": 0.5814,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28170897392252964,
      "learning_rate": 1.2495139405426606e-06,
      "loss": 0.5711,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.2818691949065334,
      "learning_rate": 1.2077882997461603e-06,
      "loss": 0.58,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.2647801935178872,
      "learning_rate": 1.1670398773471007e-06,
      "loss": 0.5801,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.2765750921897747,
      "learning_rate": 1.1272944934764177e-06,
      "loss": 0.5777,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.2863025080094374,
      "learning_rate": 1.0885773326923188e-06,
      "loss": 0.5806,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.2710069820566483,
      "learning_rate": 1.0509129280221493e-06,
      "loss": 0.582,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.2599268431610711,
      "learning_rate": 1.0143251454171064e-06,
      "loss": 0.5797,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.2882242048083095,
      "learning_rate": 9.788371686296375e-07,
      "loss": 0.5791,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.27084944120917026,
      "learning_rate": 9.444714845231223e-07,
      "loss": 0.5871,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.2621197890978649,
      "learning_rate": 9.112498688231268e-07,
      "loss": 0.5903,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.27174330531915925,
      "learning_rate": 8.791933723192731e-07,
      "loss": 0.5855,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2645225114439876,
      "learning_rate": 8.483223075264621e-07,
      "loss": 0.5829,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.2968216008645648,
      "learning_rate": 8.186562358138997e-07,
      "loss": 0.5895,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.26690120397038464,
      "learning_rate": 7.902139550100899e-07,
      "loss": 0.5824,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.2669476315054878,
      "learning_rate": 7.630134874916379e-07,
      "loss": 0.5808,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.2718088564394133,
      "learning_rate": 7.370720687634186e-07,
      "loss": 0.5801,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.26869529114920016,
      "learning_rate": 7.124061365373441e-07,
      "loss": 0.5797,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.2757696938605029,
      "learning_rate": 6.890313203166517e-07,
      "loss": 0.5799,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.2729036969143784,
      "learning_rate": 6.669624314923094e-07,
      "loss": 0.5807,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.26991231415832434,
      "learning_rate": 6.462134539578169e-07,
      "loss": 0.5839,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.26968636846310806,
      "learning_rate": 6.267975352483476e-07,
      "loss": 0.5789,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.261212066243827,
      "learning_rate": 6.087269782098488e-07,
      "loss": 0.5798,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.26843620457634154,
      "learning_rate": 5.920132332033751e-07,
      "loss": 0.583,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2630054385244121,
      "learning_rate": 5.766668908495966e-07,
      "loss": 0.5863,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.262257419716332,
      "learning_rate": 5.626976753180799e-07,
      "loss": 0.576,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2561790141333947,
      "learning_rate": 5.501144381655945e-07,
      "loss": 0.5746,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.2673685230013436,
      "learning_rate": 5.389251527273468e-07,
      "loss": 0.5894,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.2646253429218661,
      "learning_rate": 5.291369090646962e-07,
      "loss": 0.5863,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.2677992689042271,
      "learning_rate": 5.207559094725573e-07,
      "loss": 0.5834,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.27009812120249443,
      "learning_rate": 5.137874645493318e-07,
      "loss": 0.5843,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.26940782918717715,
      "learning_rate": 5.082359898318615e-07,
      "loss": 0.5745,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.26579519078241065,
      "learning_rate": 5.041050029975357e-07,
      "loss": 0.5744,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.27656234302597626,
      "learning_rate": 5.013971216353229e-07,
      "loss": 0.5756,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.2654274013759909,
      "learning_rate": 5.001140615871431e-07,
      "loss": 0.5858,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6200892925262451,
      "eval_runtime": 446.9198,
      "eval_samples_per_second": 26.454,
      "eval_steps_per_second": 0.414,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.61170773419071,
      "train_runtime": 70666.9018,
      "train_samples_per_second": 9.536,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2755219238682624.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}