{
  "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": 2.8774304487643567,
      "learning_rate": 5e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.5344540389225125,
      "learning_rate": 5e-06,
      "loss": 0.6505,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 1.5191386004765144,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 1.4141551743390433,
      "learning_rate": 5e-06,
      "loss": 0.6131,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 2.4862200047694842,
      "learning_rate": 5e-06,
      "loss": 0.6033,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.4750300815086217,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.4915548804694947,
      "learning_rate": 5e-06,
      "loss": 0.5926,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.892372524650567,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.709681770675116,
      "learning_rate": 5e-06,
      "loss": 0.5863,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 2.254618419373403,
      "learning_rate": 5e-06,
      "loss": 0.5891,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.5236540815926303,
      "learning_rate": 5e-06,
      "loss": 0.5814,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.3816913570178588,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 1.7729448633576892,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.2473090919035952,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.716302858423637,
      "learning_rate": 5e-06,
      "loss": 0.5787,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.9589952523912002,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 2.496944084572566,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 2.2336080144547434,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.7307311567783212,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.6121196330441476,
      "learning_rate": 5e-06,
      "loss": 0.5652,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.533560416197585,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.452450126915398,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.7741970920673447,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.3679529307417164,
      "learning_rate": 5e-06,
      "loss": 0.5639,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.483375368159423,
      "learning_rate": 5e-06,
      "loss": 0.5669,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.5503282129766518,
      "learning_rate": 5e-06,
      "loss": 0.5537,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.5972505520379774,
      "learning_rate": 5e-06,
      "loss": 0.5631,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.5484775869530372,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.3036495786562399,
      "learning_rate": 5e-06,
      "loss": 0.5582,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.3696617213668716,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.2340289028597662,
      "learning_rate": 5e-06,
      "loss": 0.5641,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.4123806560174987,
      "learning_rate": 5e-06,
      "loss": 0.5598,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.5967684052171425,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.2564531551518137,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.4426013993235978,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.2005036232032604,
      "learning_rate": 5e-06,
      "loss": 0.563,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.3290797941015413,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.5577348440553334,
      "learning_rate": 5e-06,
      "loss": 0.5529,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.5248581244957846,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.1332353996382762,
      "learning_rate": 5e-06,
      "loss": 0.5556,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.3714411687499122,
      "learning_rate": 5e-06,
      "loss": 0.5506,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.1484372834767997,
      "learning_rate": 5e-06,
      "loss": 0.5591,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.1107967078130156,
      "learning_rate": 5e-06,
      "loss": 0.5523,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.1798432479054304,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.3238490582363345,
      "learning_rate": 5e-06,
      "loss": 0.5491,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.1321205960261402,
      "learning_rate": 5e-06,
      "loss": 0.5538,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.2839586168848394,
      "learning_rate": 5e-06,
      "loss": 0.5544,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.0897398030657333,
      "learning_rate": 5e-06,
      "loss": 0.5512,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.1575734050873214,
      "learning_rate": 5e-06,
      "loss": 0.5479,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.06885610520839691,
      "eval_runtime": 505.9238,
      "eval_samples_per_second": 26.296,
      "eval_steps_per_second": 0.411,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.9053041856650703,
      "learning_rate": 5e-06,
      "loss": 0.5071,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.4401660522739657,
      "learning_rate": 5e-06,
      "loss": 0.4726,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.3320968796532682,
      "learning_rate": 5e-06,
      "loss": 0.4683,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.7576879811603687,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.498480760178038,
      "learning_rate": 5e-06,
      "loss": 0.4649,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.6076370988752315,
      "learning_rate": 5e-06,
      "loss": 0.4668,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 2.4418881588463153,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.5160243794923711,
      "learning_rate": 5e-06,
      "loss": 0.4699,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.6384572329110083,
      "learning_rate": 5e-06,
      "loss": 0.4684,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.5146441040161251,
      "learning_rate": 5e-06,
      "loss": 0.4612,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.8424704593389885,
      "learning_rate": 5e-06,
      "loss": 0.4689,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.2743268882656655,
      "learning_rate": 5e-06,
      "loss": 0.4648,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.3305136914110434,
      "learning_rate": 5e-06,
      "loss": 0.4688,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.2563425944618831,
      "learning_rate": 5e-06,
      "loss": 0.4703,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.2030246957550959,
      "learning_rate": 5e-06,
      "loss": 0.4706,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 1.1706301701079003,
      "learning_rate": 5e-06,
      "loss": 0.4757,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.342335289118665,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.3845959897798454,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.5821485126658388,
      "learning_rate": 5e-06,
      "loss": 0.475,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.3559346968461559,
      "learning_rate": 5e-06,
      "loss": 0.4724,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.7083072029059938,
      "learning_rate": 5e-06,
      "loss": 0.4696,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.4933144469805344,
      "learning_rate": 5e-06,
      "loss": 0.4744,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.693856562335361,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.1953534031290156,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.2282091851821244,
      "learning_rate": 5e-06,
      "loss": 0.4705,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.3246981766857313,
      "learning_rate": 5e-06,
      "loss": 0.4736,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.3640960444668195,
      "learning_rate": 5e-06,
      "loss": 0.476,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.3598652554278743,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.394674387460495,
      "learning_rate": 5e-06,
      "loss": 0.4761,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.6429795597253631,
      "learning_rate": 5e-06,
      "loss": 0.479,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.8755647208576927,
      "learning_rate": 5e-06,
      "loss": 0.4738,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.5379253414384246,
      "learning_rate": 5e-06,
      "loss": 0.4658,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.5793638860512589,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.4748529322455386,
      "learning_rate": 5e-06,
      "loss": 0.4701,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.2892727579865184,
      "learning_rate": 5e-06,
      "loss": 0.4719,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.3595053928671879,
      "learning_rate": 5e-06,
      "loss": 0.474,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.2849260840585164,
      "learning_rate": 5e-06,
      "loss": 0.474,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.35522219244357,
      "learning_rate": 5e-06,
      "loss": 0.4772,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.226173238642379,
      "learning_rate": 5e-06,
      "loss": 0.4778,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.2694514957146457,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.2788355163177385,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.2200366908384497,
      "learning_rate": 5e-06,
      "loss": 0.4783,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.247670305705125,
      "learning_rate": 5e-06,
      "loss": 0.4774,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.187274714004516,
      "learning_rate": 5e-06,
      "loss": 0.4742,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.1986542333604602,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.3407807221023489,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.0996638488393005,
      "learning_rate": 5e-06,
      "loss": 0.4833,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.1801562120830218,
      "learning_rate": 5e-06,
      "loss": 0.4819,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.2584627671933288,
      "learning_rate": 5e-06,
      "loss": 0.4827,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.06906617432832718,
      "eval_runtime": 507.4862,
      "eval_samples_per_second": 26.215,
      "eval_steps_per_second": 0.41,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 1.9542006060804669,
      "learning_rate": 5e-06,
      "loss": 0.4561,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.935000758745827,
      "learning_rate": 5e-06,
      "loss": 0.3924,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.5425227007244047,
      "learning_rate": 5e-06,
      "loss": 0.3882,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.406671374378772,
      "learning_rate": 5e-06,
      "loss": 0.3834,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.3225741000814224,
      "learning_rate": 5e-06,
      "loss": 0.3829,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.3087854581289653,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.5055247128397313,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.3253448003192276,
      "learning_rate": 5e-06,
      "loss": 0.3867,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.2671985080624293,
      "learning_rate": 5e-06,
      "loss": 0.3909,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.455516007687749,
      "learning_rate": 5e-06,
      "loss": 0.3887,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.3748988810626455,
      "learning_rate": 5e-06,
      "loss": 0.3865,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.3586092724615417,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.3431131885693126,
      "learning_rate": 5e-06,
      "loss": 0.3909,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.2858382727150257,
      "learning_rate": 5e-06,
      "loss": 0.3937,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.3631461037325234,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.3945141903005032,
      "learning_rate": 5e-06,
      "loss": 0.391,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.5759793822570192,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 2.039342813633422,
      "learning_rate": 5e-06,
      "loss": 0.3977,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.6975446566072463,
      "learning_rate": 5e-06,
      "loss": 0.3977,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.802922366861523,
      "learning_rate": 5e-06,
      "loss": 0.3969,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.854331261983343,
      "learning_rate": 5e-06,
      "loss": 0.3958,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.4940689520172188,
      "learning_rate": 5e-06,
      "loss": 0.3938,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.7259555359811671,
      "learning_rate": 5e-06,
      "loss": 0.3929,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.5736139090062196,
      "learning_rate": 5e-06,
      "loss": 0.3969,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.4329253407509266,
      "learning_rate": 5e-06,
      "loss": 0.3967,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.4901567005006235,
      "learning_rate": 5e-06,
      "loss": 0.4009,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.3522242258508488,
      "learning_rate": 5e-06,
      "loss": 0.3951,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.536738400126712,
      "learning_rate": 5e-06,
      "loss": 0.3913,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.2953991724559513,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.2523173423982397,
      "learning_rate": 5e-06,
      "loss": 0.3996,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.3336723981706788,
      "learning_rate": 5e-06,
      "loss": 0.4052,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.472845603089787,
      "learning_rate": 5e-06,
      "loss": 0.4003,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.288987152067692,
      "learning_rate": 5e-06,
      "loss": 0.3998,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.403806833032338,
      "learning_rate": 5e-06,
      "loss": 0.4027,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.272279373249665,
      "learning_rate": 5e-06,
      "loss": 0.405,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.3816960642618357,
      "learning_rate": 5e-06,
      "loss": 0.403,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.3287384175883568,
      "learning_rate": 5e-06,
      "loss": 0.403,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.3061458943923105,
      "learning_rate": 5e-06,
      "loss": 0.3987,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.5895834597948455,
      "learning_rate": 5e-06,
      "loss": 0.4048,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.3507916034552265,
      "learning_rate": 5e-06,
      "loss": 0.402,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.4325413783265324,
      "learning_rate": 5e-06,
      "loss": 0.4048,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.2903382408076844,
      "learning_rate": 5e-06,
      "loss": 0.3986,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.337292137509307,
      "learning_rate": 5e-06,
      "loss": 0.4068,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.2790521065554994,
      "learning_rate": 5e-06,
      "loss": 0.4032,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.2629153464134446,
      "learning_rate": 5e-06,
      "loss": 0.4041,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.3603753931715636,
      "learning_rate": 5e-06,
      "loss": 0.4065,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.3567858575980736,
      "learning_rate": 5e-06,
      "loss": 0.4155,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.2575983614178015,
      "learning_rate": 5e-06,
      "loss": 0.4037,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.3268109235441432,
      "learning_rate": 5e-06,
      "loss": 0.4073,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.07261991500854492,
      "eval_runtime": 504.5612,
      "eval_samples_per_second": 26.367,
      "eval_steps_per_second": 0.412,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.4815750637918489,
      "train_runtime": 84061.7352,
      "train_samples_per_second": 9.02,
      "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
}