{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9954430379746837,
  "eval_steps": 500,
  "global_step": 1479,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 2.87827745867407,
      "learning_rate": 5e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 1.503561140644729,
      "learning_rate": 5e-06,
      "loss": 0.6503,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.123832579641692,
      "learning_rate": 5e-06,
      "loss": 0.6292,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 2.483543539358744,
      "learning_rate": 5e-06,
      "loss": 0.6143,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 3.1137171355537596,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 2.1323225795168197,
      "learning_rate": 5e-06,
      "loss": 0.5997,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 2.376775001196459,
      "learning_rate": 5e-06,
      "loss": 0.5929,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 2.091084104740345,
      "learning_rate": 5e-06,
      "loss": 0.5875,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.826940524074478,
      "learning_rate": 5e-06,
      "loss": 0.587,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 1.9479364612270518,
      "learning_rate": 5e-06,
      "loss": 0.5907,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.347191359421055,
      "learning_rate": 5e-06,
      "loss": 0.5827,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.9133596604397143,
      "learning_rate": 5e-06,
      "loss": 0.5808,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 2.0856825923282267,
      "learning_rate": 5e-06,
      "loss": 0.5802,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 2.0659242188607956,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 2.2242625115350734,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.8493284215044559,
      "learning_rate": 5e-06,
      "loss": 0.5767,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.3225390188066017,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.3144122187155802,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.7839547587154652,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.5005508777203775,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 2.174274523481402,
      "learning_rate": 5e-06,
      "loss": 0.5633,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.5113632129844095,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.5961494370169218,
      "learning_rate": 5e-06,
      "loss": 0.5666,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.288933659885077,
      "learning_rate": 5e-06,
      "loss": 0.5627,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.6994245400700525,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.3467375726641135,
      "learning_rate": 5e-06,
      "loss": 0.5535,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.2021029764768774,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.3221968373920874,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.6029029271821804,
      "learning_rate": 5e-06,
      "loss": 0.5588,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.2778115077613206,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.3927199582819663,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.5546344257632736,
      "learning_rate": 5e-06,
      "loss": 0.5603,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.448618383312863,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.1945889777563863,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.4203008537995743,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.294027054310451,
      "learning_rate": 5e-06,
      "loss": 0.5627,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.3574046507969022,
      "learning_rate": 5e-06,
      "loss": 0.5552,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.3336793484262794,
      "learning_rate": 5e-06,
      "loss": 0.5521,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.6010447849677887,
      "learning_rate": 5e-06,
      "loss": 0.5551,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.3255182802084453,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.321395724070389,
      "learning_rate": 5e-06,
      "loss": 0.5497,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.7486789392435347,
      "learning_rate": 5e-06,
      "loss": 0.5577,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.4872392393574696,
      "learning_rate": 5e-06,
      "loss": 0.5509,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.651382573809848,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.8407914400881014,
      "learning_rate": 5e-06,
      "loss": 0.5464,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.0501498460964693,
      "learning_rate": 5e-06,
      "loss": 0.5505,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.3432506131036746,
      "learning_rate": 5e-06,
      "loss": 0.5512,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.083962971844798,
      "learning_rate": 5e-06,
      "loss": 0.5495,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.1086979484947683,
      "learning_rate": 5e-06,
      "loss": 0.5468,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.06877824664115906,
      "eval_runtime": 505.5411,
      "eval_samples_per_second": 26.316,
      "eval_steps_per_second": 0.411,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.8485240719148788,
      "learning_rate": 5e-06,
      "loss": 0.5077,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.7207406864243355,
      "learning_rate": 5e-06,
      "loss": 0.474,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.7605583118605725,
      "learning_rate": 5e-06,
      "loss": 0.4691,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.7540580619788109,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.8627897209874755,
      "learning_rate": 5e-06,
      "loss": 0.4675,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.1866316770300258,
      "learning_rate": 5e-06,
      "loss": 0.4691,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.285428737977006,
      "learning_rate": 5e-06,
      "loss": 0.4668,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.0755903842934518,
      "learning_rate": 5e-06,
      "loss": 0.4733,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.1902818340216896,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.1694822163666938,
      "learning_rate": 5e-06,
      "loss": 0.4681,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.2760418235824538,
      "learning_rate": 5e-06,
      "loss": 0.4755,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.5012572561860649,
      "learning_rate": 5e-06,
      "loss": 0.4713,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.5067938164477366,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.2650891339298898,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 2.126175368368165,
      "learning_rate": 5e-06,
      "loss": 0.4743,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 2.1033581382111515,
      "learning_rate": 5e-06,
      "loss": 0.4779,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.9285784407321582,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.467126307389376,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.171845721479099,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.1211119608578521,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.2813381206036762,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.2142562775975203,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.3065892235328609,
      "learning_rate": 5e-06,
      "loss": 0.4799,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.2091385470266953,
      "learning_rate": 5e-06,
      "loss": 0.482,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.1900985526322274,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.2130040834421485,
      "learning_rate": 5e-06,
      "loss": 0.4775,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.210742050172995,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.3054877926673427,
      "learning_rate": 5e-06,
      "loss": 0.4775,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.191618406053031,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.3824775280514061,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.5333565962575166,
      "learning_rate": 5e-06,
      "loss": 0.4766,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.3550298017516011,
      "learning_rate": 5e-06,
      "loss": 0.468,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.379283656581002,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.3034230808351315,
      "learning_rate": 5e-06,
      "loss": 0.4724,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.1433175764894465,
      "learning_rate": 5e-06,
      "loss": 0.4746,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.1553619260979469,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.1832171041867154,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.1225786689368586,
      "learning_rate": 5e-06,
      "loss": 0.4809,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.1162988281153534,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.146918495687925,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.1648480111487047,
      "learning_rate": 5e-06,
      "loss": 0.4779,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.1330271907981668,
      "learning_rate": 5e-06,
      "loss": 0.4799,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.1850479693557765,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.1090823745833138,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.2148080990270176,
      "learning_rate": 5e-06,
      "loss": 0.4794,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.395739516166439,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.5036803554145426,
      "learning_rate": 5e-06,
      "loss": 0.4841,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.2075646921541712,
      "learning_rate": 5e-06,
      "loss": 0.4821,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.386161895569186,
      "learning_rate": 5e-06,
      "loss": 0.4823,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.06866108626127243,
      "eval_runtime": 508.9298,
      "eval_samples_per_second": 26.141,
      "eval_steps_per_second": 0.409,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 1.9622488088995311,
      "learning_rate": 5e-06,
      "loss": 0.4544,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.718943768896692,
      "learning_rate": 5e-06,
      "loss": 0.3907,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.5251966880306207,
      "learning_rate": 5e-06,
      "loss": 0.3873,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.409960741043503,
      "learning_rate": 5e-06,
      "loss": 0.3833,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.3830947877082551,
      "learning_rate": 5e-06,
      "loss": 0.3837,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.2455197267461406,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.7347943483326818,
      "learning_rate": 5e-06,
      "loss": 0.3916,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.7912959357909501,
      "learning_rate": 5e-06,
      "loss": 0.3869,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.9396975431899355,
      "learning_rate": 5e-06,
      "loss": 0.3903,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.815293883355671,
      "learning_rate": 5e-06,
      "loss": 0.3883,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.566406201629351,
      "learning_rate": 5e-06,
      "loss": 0.3849,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.3397398739391921,
      "learning_rate": 5e-06,
      "loss": 0.3934,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.484745943108369,
      "learning_rate": 5e-06,
      "loss": 0.3893,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.3492715383326803,
      "learning_rate": 5e-06,
      "loss": 0.3916,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.3545673158149851,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.3320490351992074,
      "learning_rate": 5e-06,
      "loss": 0.39,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.360504116582008,
      "learning_rate": 5e-06,
      "loss": 0.3967,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 2.0776169928432555,
      "learning_rate": 5e-06,
      "loss": 0.3973,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.751560740272,
      "learning_rate": 5e-06,
      "loss": 0.3981,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.89921373150235,
      "learning_rate": 5e-06,
      "loss": 0.3971,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.8344801623124742,
      "learning_rate": 5e-06,
      "loss": 0.3958,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.8787799011008097,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.5713972585821883,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.3295921794914953,
      "learning_rate": 5e-06,
      "loss": 0.3963,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.4896125125414852,
      "learning_rate": 5e-06,
      "loss": 0.3968,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.478242379215419,
      "learning_rate": 5e-06,
      "loss": 0.4012,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.5280530580215625,
      "learning_rate": 5e-06,
      "loss": 0.3951,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.4435829996677498,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.5947302968346873,
      "learning_rate": 5e-06,
      "loss": 0.3981,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.3519943793082068,
      "learning_rate": 5e-06,
      "loss": 0.3999,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.3204383277858538,
      "learning_rate": 5e-06,
      "loss": 0.4049,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.4690586571352935,
      "learning_rate": 5e-06,
      "loss": 0.3997,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.238988513040474,
      "learning_rate": 5e-06,
      "loss": 0.3993,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.39236363280309,
      "learning_rate": 5e-06,
      "loss": 0.4023,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.2918366741129463,
      "learning_rate": 5e-06,
      "loss": 0.4048,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.390314130008641,
      "learning_rate": 5e-06,
      "loss": 0.4032,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.2756711737710027,
      "learning_rate": 5e-06,
      "loss": 0.4028,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.2957542776214626,
      "learning_rate": 5e-06,
      "loss": 0.3986,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.4152635056630003,
      "learning_rate": 5e-06,
      "loss": 0.4047,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.3310678155808195,
      "learning_rate": 5e-06,
      "loss": 0.4021,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.4211085462606632,
      "learning_rate": 5e-06,
      "loss": 0.4049,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.257914162122748,
      "learning_rate": 5e-06,
      "loss": 0.3984,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.370221439227086,
      "learning_rate": 5e-06,
      "loss": 0.4067,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.25831040242536,
      "learning_rate": 5e-06,
      "loss": 0.4025,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.304550201225735,
      "learning_rate": 5e-06,
      "loss": 0.4036,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.3387469706775894,
      "learning_rate": 5e-06,
      "loss": 0.4057,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.307624374883293,
      "learning_rate": 5e-06,
      "loss": 0.4145,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.384227367004548,
      "learning_rate": 5e-06,
      "loss": 0.4023,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.3020656705807938,
      "learning_rate": 5e-06,
      "loss": 0.4067,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.07244078814983368,
      "eval_runtime": 509.7055,
      "eval_samples_per_second": 26.101,
      "eval_steps_per_second": 0.408,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.4823839582245925,
      "train_runtime": 84586.1483,
      "train_samples_per_second": 8.965,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1479,
  "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": 2477170706350080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}