{
  "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": 2.8877771911403016,
      "learning_rate": 5e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.2294834485187973,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.4547588475293103,
      "learning_rate": 5e-06,
      "loss": 0.629,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 2.0443878280598624,
      "learning_rate": 5e-06,
      "loss": 0.6134,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 1.5102886423214212,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.4856866018507489,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.5316356840206717,
      "learning_rate": 5e-06,
      "loss": 0.5922,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.7147665128956195,
      "learning_rate": 5e-06,
      "loss": 0.5877,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.7308970189870827,
      "learning_rate": 5e-06,
      "loss": 0.5869,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 2.2908677489633327,
      "learning_rate": 5e-06,
      "loss": 0.5894,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.354241491190274,
      "learning_rate": 5e-06,
      "loss": 0.5815,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.3948248922862374,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 2.2718824029357347,
      "learning_rate": 5e-06,
      "loss": 0.5781,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 2.1060380654628625,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.6323986172543352,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.5001325556393612,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 2.19381837761027,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 2.0646731852381044,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.5335478355598067,
      "learning_rate": 5e-06,
      "loss": 0.5708,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.3945582055615051,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.3897842852914954,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.4935312375590064,
      "learning_rate": 5e-06,
      "loss": 0.5665,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.7518839161142288,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.1585796963266615,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.2966452791221394,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.5279441262749707,
      "learning_rate": 5e-06,
      "loss": 0.5528,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.4864965256894778,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.6172726228041323,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.309516691642357,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.3060937890001645,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.2379596944740083,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.2060237317202396,
      "learning_rate": 5e-06,
      "loss": 0.561,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.3300076458783476,
      "learning_rate": 5e-06,
      "loss": 0.561,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.298934921391733,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.34396713861144,
      "learning_rate": 5e-06,
      "loss": 0.5619,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.230038251173589,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.2916876849266508,
      "learning_rate": 5e-06,
      "loss": 0.5561,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.4062727584587997,
      "learning_rate": 5e-06,
      "loss": 0.5528,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.8176516191927978,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.1154026747296282,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.4178981343708785,
      "learning_rate": 5e-06,
      "loss": 0.5505,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.1213120675703767,
      "learning_rate": 5e-06,
      "loss": 0.5589,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.2510408891414735,
      "learning_rate": 5e-06,
      "loss": 0.5521,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.1502044804280906,
      "learning_rate": 5e-06,
      "loss": 0.5578,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.4085741123286435,
      "learning_rate": 5e-06,
      "loss": 0.5491,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.0314952283107646,
      "learning_rate": 5e-06,
      "loss": 0.5534,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.392988455426854,
      "learning_rate": 5e-06,
      "loss": 0.5543,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.0962802919223296,
      "learning_rate": 5e-06,
      "loss": 0.5513,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.1019400606381653,
      "learning_rate": 5e-06,
      "loss": 0.5479,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.0688617154955864,
      "eval_runtime": 506.5979,
      "eval_samples_per_second": 26.261,
      "eval_steps_per_second": 0.411,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.9265333502006505,
      "learning_rate": 5e-06,
      "loss": 0.5076,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.9664694257097348,
      "learning_rate": 5e-06,
      "loss": 0.4727,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.7942783041476533,
      "learning_rate": 5e-06,
      "loss": 0.4674,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 2.3027454914122107,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.6756627768032348,
      "learning_rate": 5e-06,
      "loss": 0.4652,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.3357692446389655,
      "learning_rate": 5e-06,
      "loss": 0.4668,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.2874290505413306,
      "learning_rate": 5e-06,
      "loss": 0.4634,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.1486343814753555,
      "learning_rate": 5e-06,
      "loss": 0.4706,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.2063227401232046,
      "learning_rate": 5e-06,
      "loss": 0.4705,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.184320963931943,
      "learning_rate": 5e-06,
      "loss": 0.4653,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.3358636951088882,
      "learning_rate": 5e-06,
      "loss": 0.4731,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.425133318797002,
      "learning_rate": 5e-06,
      "loss": 0.4689,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.6364325943594298,
      "learning_rate": 5e-06,
      "loss": 0.4729,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.318673316672248,
      "learning_rate": 5e-06,
      "loss": 0.4732,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.3122002263891996,
      "learning_rate": 5e-06,
      "loss": 0.4722,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 2.1508251935281733,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.863930986406004,
      "learning_rate": 5e-06,
      "loss": 0.4639,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.4719212499856806,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.414514809425289,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.6000497017103448,
      "learning_rate": 5e-06,
      "loss": 0.4723,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.400047845824815,
      "learning_rate": 5e-06,
      "loss": 0.4708,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.3238131935441257,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.2381301593371368,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.3586544382551995,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.2020207137782775,
      "learning_rate": 5e-06,
      "loss": 0.4721,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.2396166262877506,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.1667049104651803,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.273616512026121,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.1889561098260564,
      "learning_rate": 5e-06,
      "loss": 0.4764,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.1503189703578973,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.4278882590555009,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.183071414253031,
      "learning_rate": 5e-06,
      "loss": 0.4682,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.3960016943164528,
      "learning_rate": 5e-06,
      "loss": 0.4773,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.2320788611563414,
      "learning_rate": 5e-06,
      "loss": 0.4728,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.3108466956318439,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.181031459769793,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.1302662753413042,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.127889601843092,
      "learning_rate": 5e-06,
      "loss": 0.4804,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.145481859966167,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.2363679424934566,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.2389482233566855,
      "learning_rate": 5e-06,
      "loss": 0.4776,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.1716310226253532,
      "learning_rate": 5e-06,
      "loss": 0.4796,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.2634817133278293,
      "learning_rate": 5e-06,
      "loss": 0.4783,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.0975216253496476,
      "learning_rate": 5e-06,
      "loss": 0.4749,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.1740097191762555,
      "learning_rate": 5e-06,
      "loss": 0.4789,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.6550569156768484,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.5015715849094382,
      "learning_rate": 5e-06,
      "loss": 0.4842,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.0921513269169847,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.3708525343966105,
      "learning_rate": 5e-06,
      "loss": 0.481,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.06875930726528168,
      "eval_runtime": 509.0527,
      "eval_samples_per_second": 26.135,
      "eval_steps_per_second": 0.409,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 1.9154494703196068,
      "learning_rate": 5e-06,
      "loss": 0.4531,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.979264846486845,
      "learning_rate": 5e-06,
      "loss": 0.3866,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.4526649203181639,
      "learning_rate": 5e-06,
      "loss": 0.3822,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.4220994888729301,
      "learning_rate": 5e-06,
      "loss": 0.3784,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.3393673769442962,
      "learning_rate": 5e-06,
      "loss": 0.3788,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.277014029344912,
      "learning_rate": 5e-06,
      "loss": 0.3764,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.5340314098900096,
      "learning_rate": 5e-06,
      "loss": 0.3868,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.6508873941026114,
      "learning_rate": 5e-06,
      "loss": 0.3822,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.407606446135562,
      "learning_rate": 5e-06,
      "loss": 0.3862,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.411050375863623,
      "learning_rate": 5e-06,
      "loss": 0.384,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.3248395383039557,
      "learning_rate": 5e-06,
      "loss": 0.3819,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.3819331833896153,
      "learning_rate": 5e-06,
      "loss": 0.3912,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.2436936664526173,
      "learning_rate": 5e-06,
      "loss": 0.3874,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.2684331146489296,
      "learning_rate": 5e-06,
      "loss": 0.39,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.5794913167245803,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.3748398729318,
      "learning_rate": 5e-06,
      "loss": 0.3875,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 93.67781801844193,
      "learning_rate": 5e-06,
      "loss": 0.3941,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 1.6658805973526587,
      "learning_rate": 5e-06,
      "loss": 0.3937,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.387380031309021,
      "learning_rate": 5e-06,
      "loss": 0.3929,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.286285420789643,
      "learning_rate": 5e-06,
      "loss": 0.3925,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.2998738300592168,
      "learning_rate": 5e-06,
      "loss": 0.3926,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.5793445810769084,
      "learning_rate": 5e-06,
      "loss": 0.3917,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.2740544518977726,
      "learning_rate": 5e-06,
      "loss": 0.392,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.23865480155546,
      "learning_rate": 5e-06,
      "loss": 0.3945,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.3769287033825384,
      "learning_rate": 5e-06,
      "loss": 0.3948,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.4266978552229843,
      "learning_rate": 5e-06,
      "loss": 0.3994,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.3743424703937366,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.475562880517447,
      "learning_rate": 5e-06,
      "loss": 0.3887,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.3396408438411616,
      "learning_rate": 5e-06,
      "loss": 0.3951,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.3394788659237564,
      "learning_rate": 5e-06,
      "loss": 0.3969,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.373851456706019,
      "learning_rate": 5e-06,
      "loss": 0.4018,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.4504759405093464,
      "learning_rate": 5e-06,
      "loss": 0.397,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.254741242014257,
      "learning_rate": 5e-06,
      "loss": 0.3972,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.5197421689722739,
      "learning_rate": 5e-06,
      "loss": 0.4001,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.2789775046223264,
      "learning_rate": 5e-06,
      "loss": 0.4023,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.4778301872403103,
      "learning_rate": 5e-06,
      "loss": 0.4004,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.2954290946299785,
      "learning_rate": 5e-06,
      "loss": 0.3999,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.2598940164892094,
      "learning_rate": 5e-06,
      "loss": 0.3955,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.4352391902300061,
      "learning_rate": 5e-06,
      "loss": 0.4017,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.3764405845983565,
      "learning_rate": 5e-06,
      "loss": 0.3994,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.4992747448014379,
      "learning_rate": 5e-06,
      "loss": 0.4019,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.2897539200248462,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.275567652965357,
      "learning_rate": 5e-06,
      "loss": 0.4043,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.3040786299424412,
      "learning_rate": 5e-06,
      "loss": 0.4001,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.3229679573518474,
      "learning_rate": 5e-06,
      "loss": 0.4007,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.3751034663278319,
      "learning_rate": 5e-06,
      "loss": 0.4032,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.332106303867251,
      "learning_rate": 5e-06,
      "loss": 0.4118,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.4514797774998427,
      "learning_rate": 5e-06,
      "loss": 0.3999,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.2854548452051338,
      "learning_rate": 5e-06,
      "loss": 0.404,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.07273153215646744,
      "eval_runtime": 508.6931,
      "eval_samples_per_second": 26.153,
      "eval_steps_per_second": 0.409,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.4808535206712848,
      "train_runtime": 84482.3839,
      "train_samples_per_second": 8.976,
      "train_steps_per_second": 0.018
    }
  ],
  "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
}