{
  "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": 2.88220611268731,
      "learning_rate": 5e-06,
      "loss": 0.7569,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.480067861484698,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.774980923077334,
      "learning_rate": 5e-06,
      "loss": 0.629,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 1.7240706644388326,
      "learning_rate": 5e-06,
      "loss": 0.6134,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 1.4536613830159735,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.450284463333836,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.6558140046758392,
      "learning_rate": 5e-06,
      "loss": 0.5925,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.7520091331371848,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.6029120553311094,
      "learning_rate": 5e-06,
      "loss": 0.5865,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 1.567363166768414,
      "learning_rate": 5e-06,
      "loss": 0.5893,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.4694354120450246,
      "learning_rate": 5e-06,
      "loss": 0.5819,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.4681818695060211,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 1.5191462196175605,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.3078880356772522,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.486087097355444,
      "learning_rate": 5e-06,
      "loss": 0.5784,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.1938431479309142,
      "learning_rate": 5e-06,
      "loss": 0.5766,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.702252307631795,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 2.724877827601554,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.9757209917803782,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 2.0877685409506817,
      "learning_rate": 5e-06,
      "loss": 0.5651,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.562380367481087,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.6767077949693185,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.2635841301185957,
      "learning_rate": 5e-06,
      "loss": 0.5661,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.6125913827261849,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 2.097566919302689,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.225603648815228,
      "learning_rate": 5e-06,
      "loss": 0.5536,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 2.6536486037387843,
      "learning_rate": 5e-06,
      "loss": 0.5626,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 2.061044706332861,
      "learning_rate": 5e-06,
      "loss": 0.5578,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.3385785865849447,
      "learning_rate": 5e-06,
      "loss": 0.556,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.4454247513778045,
      "learning_rate": 5e-06,
      "loss": 0.556,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.7204398183201466,
      "learning_rate": 5e-06,
      "loss": 0.562,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.9793942130611824,
      "learning_rate": 5e-06,
      "loss": 0.5578,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.7805954913632007,
      "learning_rate": 5e-06,
      "loss": 0.5573,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.6398542655595056,
      "learning_rate": 5e-06,
      "loss": 0.5568,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.4219457540606182,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.205446257048794,
      "learning_rate": 5e-06,
      "loss": 0.5621,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.5519028320645483,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.3405556096272386,
      "learning_rate": 5e-06,
      "loss": 0.5529,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.1970424265714363,
      "learning_rate": 5e-06,
      "loss": 0.556,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.4143181030859675,
      "learning_rate": 5e-06,
      "loss": 0.5568,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.2868527954949525,
      "learning_rate": 5e-06,
      "loss": 0.5519,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.307968999368857,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.1315498091126373,
      "learning_rate": 5e-06,
      "loss": 0.5527,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.333424078805594,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.2209294815766687,
      "learning_rate": 5e-06,
      "loss": 0.5496,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.1522504991077107,
      "learning_rate": 5e-06,
      "loss": 0.554,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.111876381365586,
      "learning_rate": 5e-06,
      "loss": 0.5549,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.0648075841701097,
      "learning_rate": 5e-06,
      "loss": 0.5508,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.2354318647376354,
      "learning_rate": 5e-06,
      "loss": 0.5479,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.06881221383810043,
      "eval_runtime": 505.2683,
      "eval_samples_per_second": 26.331,
      "eval_steps_per_second": 0.412,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 2.1556327804060715,
      "learning_rate": 5e-06,
      "loss": 0.5079,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.4832590670609553,
      "learning_rate": 5e-06,
      "loss": 0.4736,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.6271105981188392,
      "learning_rate": 5e-06,
      "loss": 0.4689,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.6518604720423575,
      "learning_rate": 5e-06,
      "loss": 0.4721,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.6306680005909122,
      "learning_rate": 5e-06,
      "loss": 0.4685,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.5490864800468693,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.4729491530388399,
      "learning_rate": 5e-06,
      "loss": 0.4691,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.2846484466684625,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.210269025129285,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.1994849011298538,
      "learning_rate": 5e-06,
      "loss": 0.4686,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.3109012503883226,
      "learning_rate": 5e-06,
      "loss": 0.4763,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.361668676774227,
      "learning_rate": 5e-06,
      "loss": 0.4728,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.464666048188549,
      "learning_rate": 5e-06,
      "loss": 0.4772,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.4141750327340763,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.143860086864536,
      "learning_rate": 5e-06,
      "loss": 0.4758,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 1.268594443588833,
      "learning_rate": 5e-06,
      "loss": 0.4796,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.2924687305619194,
      "learning_rate": 5e-06,
      "loss": 0.469,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.2741990803305674,
      "learning_rate": 5e-06,
      "loss": 0.4829,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.4171124530128463,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.1461018430295604,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.2574652457742375,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.2661309102833118,
      "learning_rate": 5e-06,
      "loss": 0.4814,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.1981819216436724,
      "learning_rate": 5e-06,
      "loss": 0.4802,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.55940798073831,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.2417973039908028,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.1387382430999369,
      "learning_rate": 5e-06,
      "loss": 0.4781,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.104717023280076,
      "learning_rate": 5e-06,
      "loss": 0.4795,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.3153249018888995,
      "learning_rate": 5e-06,
      "loss": 0.4795,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.1992568131579366,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.136040651878267,
      "learning_rate": 5e-06,
      "loss": 0.482,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.3304817212078788,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.142527655189943,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.4128828061541685,
      "learning_rate": 5e-06,
      "loss": 0.4801,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.1980978216324385,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.262563541243328,
      "learning_rate": 5e-06,
      "loss": 0.4776,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.2436924983133957,
      "learning_rate": 5e-06,
      "loss": 0.4801,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.39666723634599,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.2842653152149013,
      "learning_rate": 5e-06,
      "loss": 0.4825,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.165392419546629,
      "learning_rate": 5e-06,
      "loss": 0.4836,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.1855160731969316,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.2464436535452346,
      "learning_rate": 5e-06,
      "loss": 0.4794,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.1709360612380009,
      "learning_rate": 5e-06,
      "loss": 0.4815,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.2208910287918922,
      "learning_rate": 5e-06,
      "loss": 0.4805,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.0888496188915995,
      "learning_rate": 5e-06,
      "loss": 0.4775,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.1994340934717456,
      "learning_rate": 5e-06,
      "loss": 0.4814,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.2945338868463476,
      "learning_rate": 5e-06,
      "loss": 0.4818,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.6313486116488276,
      "learning_rate": 5e-06,
      "loss": 0.4858,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.2011513392392508,
      "learning_rate": 5e-06,
      "loss": 0.4844,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.5089522220254115,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.06875146180391312,
      "eval_runtime": 505.4208,
      "eval_samples_per_second": 26.323,
      "eval_steps_per_second": 0.412,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 1.7875364396427433,
      "learning_rate": 5e-06,
      "loss": 0.4553,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.6493678627855817,
      "learning_rate": 5e-06,
      "loss": 0.386,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.42447013081262,
      "learning_rate": 5e-06,
      "loss": 0.3825,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.4117353579299758,
      "learning_rate": 5e-06,
      "loss": 0.3786,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.3771094109220838,
      "learning_rate": 5e-06,
      "loss": 0.3791,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.343133315036709,
      "learning_rate": 5e-06,
      "loss": 0.3771,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.4448432034872896,
      "learning_rate": 5e-06,
      "loss": 0.387,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.6456444944430404,
      "learning_rate": 5e-06,
      "loss": 0.3827,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.3452334022152583,
      "learning_rate": 5e-06,
      "loss": 0.3865,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.3446640669823824,
      "learning_rate": 5e-06,
      "loss": 0.3842,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.3748598440301938,
      "learning_rate": 5e-06,
      "loss": 0.3826,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.4087618626218648,
      "learning_rate": 5e-06,
      "loss": 0.3918,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.2293657724154228,
      "learning_rate": 5e-06,
      "loss": 0.3876,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.2846672502227803,
      "learning_rate": 5e-06,
      "loss": 0.3903,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.4377466610216114,
      "learning_rate": 5e-06,
      "loss": 0.3914,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.4175742620767358,
      "learning_rate": 5e-06,
      "loss": 0.388,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.5759675575520993,
      "learning_rate": 5e-06,
      "loss": 0.3933,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 1.508836056446397,
      "learning_rate": 5e-06,
      "loss": 0.3932,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.825295421372421,
      "learning_rate": 5e-06,
      "loss": 0.3944,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.3216739690036472,
      "learning_rate": 5e-06,
      "loss": 0.3943,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.3805684615677538,
      "learning_rate": 5e-06,
      "loss": 0.394,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.3512854374041294,
      "learning_rate": 5e-06,
      "loss": 0.3923,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.295908581682868,
      "learning_rate": 5e-06,
      "loss": 0.3923,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.2255128770109138,
      "learning_rate": 5e-06,
      "loss": 0.3955,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.3685809804833307,
      "learning_rate": 5e-06,
      "loss": 0.3957,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.4762862327728246,
      "learning_rate": 5e-06,
      "loss": 0.3999,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.3415537378198834,
      "learning_rate": 5e-06,
      "loss": 0.3939,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.4898621089248945,
      "learning_rate": 5e-06,
      "loss": 0.3895,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.8618471579741513,
      "learning_rate": 5e-06,
      "loss": 0.3962,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.639428963357603,
      "learning_rate": 5e-06,
      "loss": 0.3976,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.3573195616422664,
      "learning_rate": 5e-06,
      "loss": 0.4009,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.4054413316327985,
      "learning_rate": 5e-06,
      "loss": 0.3958,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.360657435359846,
      "learning_rate": 5e-06,
      "loss": 0.3965,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.4646728739670725,
      "learning_rate": 5e-06,
      "loss": 0.3997,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.2841526066493858,
      "learning_rate": 5e-06,
      "loss": 0.4017,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.4416140658783074,
      "learning_rate": 5e-06,
      "loss": 0.4,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.289169639101135,
      "learning_rate": 5e-06,
      "loss": 0.3997,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.2983193210908834,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.4790452157324334,
      "learning_rate": 5e-06,
      "loss": 0.4022,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.3662958435730228,
      "learning_rate": 5e-06,
      "loss": 0.3993,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.5324942996261537,
      "learning_rate": 5e-06,
      "loss": 0.4018,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.363475696210741,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.2915820963572053,
      "learning_rate": 5e-06,
      "loss": 0.4038,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.2674230912928623,
      "learning_rate": 5e-06,
      "loss": 0.4001,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.2889699399012808,
      "learning_rate": 5e-06,
      "loss": 0.4006,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.2789428851698343,
      "learning_rate": 5e-06,
      "loss": 0.4026,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.386940313351875,
      "learning_rate": 5e-06,
      "loss": 0.4118,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.4388170101564672,
      "learning_rate": 5e-06,
      "loss": 0.4,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.256484387745372,
      "learning_rate": 5e-06,
      "loss": 0.4038,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.07278138399124146,
      "eval_runtime": 507.1081,
      "eval_samples_per_second": 26.235,
      "eval_steps_per_second": 0.41,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.48194751488025966,
      "train_runtime": 84452.6037,
      "train_samples_per_second": 8.979,
      "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
}