{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996011396011396,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 1.8413729954355371,
      "learning_rate": 5e-06,
      "loss": 0.7563,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.9090731736201849,
      "learning_rate": 5e-06,
      "loss": 0.7031,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9459277239616597,
      "learning_rate": 5e-06,
      "loss": 0.6819,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8734617594615591,
      "learning_rate": 5e-06,
      "loss": 0.6816,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8261584435284774,
      "learning_rate": 5e-06,
      "loss": 0.6779,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.7440549988310982,
      "learning_rate": 5e-06,
      "loss": 0.6577,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.5455785570158392,
      "learning_rate": 5e-06,
      "loss": 0.6543,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.44565303721946115,
      "learning_rate": 5e-06,
      "loss": 0.6565,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3345108653267818,
      "learning_rate": 5e-06,
      "loss": 0.6406,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.3017230444715495,
      "learning_rate": 5e-06,
      "loss": 0.6416,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.3487395918830048,
      "learning_rate": 5e-06,
      "loss": 0.6328,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3061594827931602,
      "learning_rate": 5e-06,
      "loss": 0.641,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2911872675140233,
      "learning_rate": 5e-06,
      "loss": 0.6418,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.30262387115888767,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.31911557551796654,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.3090144942423189,
      "learning_rate": 5e-06,
      "loss": 0.6416,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.3432937062863081,
      "learning_rate": 5e-06,
      "loss": 0.6334,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.2963500618383741,
      "learning_rate": 5e-06,
      "loss": 0.639,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3046405486703939,
      "learning_rate": 5e-06,
      "loss": 0.6315,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.30868284531879653,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3052199231164997,
      "learning_rate": 5e-06,
      "loss": 0.6358,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.30277698554242666,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3211995792289639,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.3084337333085751,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3288256202640419,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.29706868313775225,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3144886815645999,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3190791089525923,
      "learning_rate": 5e-06,
      "loss": 0.6421,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3249332782376004,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2890796151811709,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.29471089880956497,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3504934958900394,
      "learning_rate": 5e-06,
      "loss": 0.6293,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3060990184286491,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3289729668080366,
      "learning_rate": 5e-06,
      "loss": 0.6318,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.33222515917483914,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3207534239220903,
      "learning_rate": 5e-06,
      "loss": 0.6306,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.33215225225215206,
      "learning_rate": 5e-06,
      "loss": 0.6243,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3182925266440484,
      "learning_rate": 5e-06,
      "loss": 0.6366,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.325414228217383,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.3025365876017664,
      "learning_rate": 5e-06,
      "loss": 0.6384,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.28492973089527013,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.30734094147253904,
      "learning_rate": 5e-06,
      "loss": 0.6215,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3478513457272329,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6252126097679138,
      "eval_runtime": 440.0949,
      "eval_samples_per_second": 26.865,
      "eval_steps_per_second": 0.42,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.3488388961703569,
      "learning_rate": 5e-06,
      "loss": 0.6473,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.3329038249349578,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.2985792359841702,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.29798147636089894,
      "learning_rate": 5e-06,
      "loss": 0.5967,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.3136045258788408,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.32139743047390607,
      "learning_rate": 5e-06,
      "loss": 0.6093,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.28823096821921135,
      "learning_rate": 5e-06,
      "loss": 0.5992,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.32266798489044735,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.29656108233094763,
      "learning_rate": 5e-06,
      "loss": 0.6028,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.32368493962158085,
      "learning_rate": 5e-06,
      "loss": 0.5957,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.2887731259651382,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.3326828983225666,
      "learning_rate": 5e-06,
      "loss": 0.6026,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.2816607282940196,
      "learning_rate": 5e-06,
      "loss": 0.6041,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.3068622260530732,
      "learning_rate": 5e-06,
      "loss": 0.5981,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2693800588461558,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.3004036329413474,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.35148473854361456,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.3223179469485186,
      "learning_rate": 5e-06,
      "loss": 0.6021,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.3022220988285776,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.3135095540825169,
      "learning_rate": 5e-06,
      "loss": 0.6026,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.3093408676490943,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.3088418507383678,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.30245463513544485,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.31000122154452087,
      "learning_rate": 5e-06,
      "loss": 0.6027,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2780050823897534,
      "learning_rate": 5e-06,
      "loss": 0.5912,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.3196358258240848,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.28599364965364427,
      "learning_rate": 5e-06,
      "loss": 0.6107,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.3054349065856669,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.2958356022094109,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.33303189252258475,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.31075349861762674,
      "learning_rate": 5e-06,
      "loss": 0.5965,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.3041316275923669,
      "learning_rate": 5e-06,
      "loss": 0.5939,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.30054925578082764,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.29626082487075206,
      "learning_rate": 5e-06,
      "loss": 0.5943,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.30547959900976057,
      "learning_rate": 5e-06,
      "loss": 0.6014,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.2968969729207538,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.3190259364697627,
      "learning_rate": 5e-06,
      "loss": 0.5858,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.31206301148081805,
      "learning_rate": 5e-06,
      "loss": 0.5937,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.30153757521039576,
      "learning_rate": 5e-06,
      "loss": 0.5914,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.31684333297637707,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.30790370015451796,
      "learning_rate": 5e-06,
      "loss": 0.5997,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.3006206063192757,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.3103260667118688,
      "learning_rate": 5e-06,
      "loss": 0.5992,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.35613689693361866,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6188303232192993,
      "eval_runtime": 439.2208,
      "eval_samples_per_second": 26.918,
      "eval_steps_per_second": 0.421,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.3285187021226287,
      "learning_rate": 5e-06,
      "loss": 0.6162,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.33691597571231074,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.31663461678384935,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.35434689966692323,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.30905451143792223,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.2817008598103781,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.31760410729881533,
      "learning_rate": 5e-06,
      "loss": 0.5648,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.31805344194855023,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.31812158359352355,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.2966251323278132,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28862934268543866,
      "learning_rate": 5e-06,
      "loss": 0.5599,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.3105559198866554,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.3058494575287101,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.30374745612458004,
      "learning_rate": 5e-06,
      "loss": 0.5667,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.3137503716862055,
      "learning_rate": 5e-06,
      "loss": 0.5697,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.3515776830000683,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.3075223218995559,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.3111410180440985,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.30184704992462885,
      "learning_rate": 5e-06,
      "loss": 0.5767,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.2941540757209925,
      "learning_rate": 5e-06,
      "loss": 0.5795,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.298175427179016,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.3004944527012022,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.3169297651732949,
      "learning_rate": 5e-06,
      "loss": 0.5789,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.30842610241832297,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.2992044788640401,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.31941674485831356,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.3034725401202754,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.30719293572688333,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.2981195886569699,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.29437080866298027,
      "learning_rate": 5e-06,
      "loss": 0.5737,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.29928822023457585,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.28901219115789856,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.29779948711219933,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2870917081594304,
      "learning_rate": 5e-06,
      "loss": 0.5765,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.28170905684828323,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2970061896232385,
      "learning_rate": 5e-06,
      "loss": 0.5649,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.3163195453999029,
      "learning_rate": 5e-06,
      "loss": 0.5798,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.29779080626080356,
      "learning_rate": 5e-06,
      "loss": 0.5764,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.3028382852058591,
      "learning_rate": 5e-06,
      "loss": 0.5736,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.3016528790992581,
      "learning_rate": 5e-06,
      "loss": 0.5745,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.28870249161646794,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.30096166056048607,
      "learning_rate": 5e-06,
      "loss": 0.5649,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.3478647432780804,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.306295401189064,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.618750810623169,
      "eval_runtime": 437.9782,
      "eval_samples_per_second": 26.994,
      "eval_steps_per_second": 0.422,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6046473435615296,
      "train_runtime": 69998.9286,
      "train_samples_per_second": 9.627,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2755219238682624.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}