{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0285148514851485,
  "eval_steps": 500,
  "global_step": 650,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015841584158415842,
      "grad_norm": 0.2681642174720764,
      "learning_rate": 0.00018,
      "loss": 0.5615610122680664,
      "step": 10
    },
    {
      "epoch": 0.031683168316831684,
      "grad_norm": 0.4051491618156433,
      "learning_rate": 0.00019904559915164368,
      "loss": 0.5492567539215087,
      "step": 20
    },
    {
      "epoch": 0.047524752475247525,
      "grad_norm": 0.3502402901649475,
      "learning_rate": 0.00019798515376458114,
      "loss": 0.599879789352417,
      "step": 30
    },
    {
      "epoch": 0.06336633663366337,
      "grad_norm": 0.29962077736854553,
      "learning_rate": 0.00019692470837751858,
      "loss": 0.6249649524688721,
      "step": 40
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.23971900343894958,
      "learning_rate": 0.00019586426299045598,
      "loss": 0.5784070014953613,
      "step": 50
    },
    {
      "epoch": 0.09504950495049505,
      "grad_norm": 0.2636028826236725,
      "learning_rate": 0.00019480381760339345,
      "loss": 0.6152547359466553,
      "step": 60
    },
    {
      "epoch": 0.11089108910891089,
      "grad_norm": 0.23000255227088928,
      "learning_rate": 0.00019374337221633088,
      "loss": 0.5608311653137207,
      "step": 70
    },
    {
      "epoch": 0.12673267326732673,
      "grad_norm": 0.2468724548816681,
      "learning_rate": 0.0001926829268292683,
      "loss": 0.5768645286560059,
      "step": 80
    },
    {
      "epoch": 0.14257425742574256,
      "grad_norm": 0.2919839322566986,
      "learning_rate": 0.00019162248144220573,
      "loss": 0.5808207035064697,
      "step": 90
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.3023220896720886,
      "learning_rate": 0.0001905620360551432,
      "loss": 0.5837886810302735,
      "step": 100
    },
    {
      "epoch": 0.17425742574257425,
      "grad_norm": 0.2673959732055664,
      "learning_rate": 0.0001895015906680806,
      "loss": 0.5960847854614257,
      "step": 110
    },
    {
      "epoch": 0.1900990099009901,
      "grad_norm": 0.2474275678396225,
      "learning_rate": 0.00018844114528101803,
      "loss": 0.5560206413269043,
      "step": 120
    },
    {
      "epoch": 0.20594059405940593,
      "grad_norm": 0.26754653453826904,
      "learning_rate": 0.0001873806998939555,
      "loss": 0.5669719696044921,
      "step": 130
    },
    {
      "epoch": 0.22178217821782178,
      "grad_norm": 0.27784964442253113,
      "learning_rate": 0.0001863202545068929,
      "loss": 0.5512593746185303,
      "step": 140
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.2117505818605423,
      "learning_rate": 0.00018525980911983034,
      "loss": 0.5637025833129883,
      "step": 150
    },
    {
      "epoch": 0.25346534653465347,
      "grad_norm": 0.27500784397125244,
      "learning_rate": 0.00018419936373276777,
      "loss": 0.5528223514556885,
      "step": 160
    },
    {
      "epoch": 0.2693069306930693,
      "grad_norm": 0.2535107731819153,
      "learning_rate": 0.0001831389183457052,
      "loss": 0.5803631782531739,
      "step": 170
    },
    {
      "epoch": 0.2851485148514851,
      "grad_norm": 0.24596087634563446,
      "learning_rate": 0.00018207847295864264,
      "loss": 0.5421345710754395,
      "step": 180
    },
    {
      "epoch": 0.300990099009901,
      "grad_norm": 0.25067201256752014,
      "learning_rate": 0.00018101802757158005,
      "loss": 0.5549107074737549,
      "step": 190
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.24968267977237701,
      "learning_rate": 0.0001799575821845175,
      "loss": 0.5486234188079834,
      "step": 200
    },
    {
      "epoch": 0.3326732673267327,
      "grad_norm": 0.24873675405979156,
      "learning_rate": 0.00017889713679745495,
      "loss": 0.5631236553192138,
      "step": 210
    },
    {
      "epoch": 0.3485148514851485,
      "grad_norm": 0.2490004599094391,
      "learning_rate": 0.00017783669141039236,
      "loss": 0.538916015625,
      "step": 220
    },
    {
      "epoch": 0.36435643564356435,
      "grad_norm": 0.193207785487175,
      "learning_rate": 0.00017677624602332982,
      "loss": 0.5809069156646729,
      "step": 230
    },
    {
      "epoch": 0.3801980198019802,
      "grad_norm": 0.28708136081695557,
      "learning_rate": 0.00017571580063626725,
      "loss": 0.5487487316131592,
      "step": 240
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.22866445779800415,
      "learning_rate": 0.00017465535524920466,
      "loss": 0.560062313079834,
      "step": 250
    },
    {
      "epoch": 0.41188118811881186,
      "grad_norm": 0.26000362634658813,
      "learning_rate": 0.0001735949098621421,
      "loss": 0.5541458129882812,
      "step": 260
    },
    {
      "epoch": 0.4277227722772277,
      "grad_norm": 0.20908737182617188,
      "learning_rate": 0.00017253446447507956,
      "loss": 0.5644277572631836,
      "step": 270
    },
    {
      "epoch": 0.44356435643564357,
      "grad_norm": 0.24441300332546234,
      "learning_rate": 0.00017147401908801697,
      "loss": 0.5405750274658203,
      "step": 280
    },
    {
      "epoch": 0.4594059405940594,
      "grad_norm": 0.23231364786624908,
      "learning_rate": 0.0001704135737009544,
      "loss": 0.5533739566802979,
      "step": 290
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.24838413298130035,
      "learning_rate": 0.00016935312831389186,
      "loss": 0.581938648223877,
      "step": 300
    },
    {
      "epoch": 0.4910891089108911,
      "grad_norm": 0.225566104054451,
      "learning_rate": 0.00016829268292682927,
      "loss": 0.5625068664550781,
      "step": 310
    },
    {
      "epoch": 0.5069306930693069,
      "grad_norm": 0.23124399781227112,
      "learning_rate": 0.0001672322375397667,
      "loss": 0.5552542209625244,
      "step": 320
    },
    {
      "epoch": 0.5227722772277228,
      "grad_norm": 0.21427498757839203,
      "learning_rate": 0.00016617179215270414,
      "loss": 0.5192074298858642,
      "step": 330
    },
    {
      "epoch": 0.5386138613861386,
      "grad_norm": 0.23526982963085175,
      "learning_rate": 0.00016511134676564158,
      "loss": 0.5778728008270264,
      "step": 340
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 0.25358083844184875,
      "learning_rate": 0.000164050901378579,
      "loss": 0.5592835903167724,
      "step": 350
    },
    {
      "epoch": 0.5702970297029702,
      "grad_norm": 0.2464510053396225,
      "learning_rate": 0.00016299045599151645,
      "loss": 0.5713228225708008,
      "step": 360
    },
    {
      "epoch": 0.5861386138613861,
      "grad_norm": 0.23266883194446564,
      "learning_rate": 0.00016193001060445388,
      "loss": 0.5558922290802002,
      "step": 370
    },
    {
      "epoch": 0.601980198019802,
      "grad_norm": 0.29434841871261597,
      "learning_rate": 0.00016086956521739132,
      "loss": 0.5865880489349365,
      "step": 380
    },
    {
      "epoch": 0.6178217821782178,
      "grad_norm": 0.20487159490585327,
      "learning_rate": 0.00015980911983032873,
      "loss": 0.5610895156860352,
      "step": 390
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.26936978101730347,
      "learning_rate": 0.0001587486744432662,
      "loss": 0.5487852096557617,
      "step": 400
    },
    {
      "epoch": 0.6495049504950495,
      "grad_norm": 0.2274005264043808,
      "learning_rate": 0.00015768822905620362,
      "loss": 0.5496184349060058,
      "step": 410
    },
    {
      "epoch": 0.6653465346534654,
      "grad_norm": 0.24373526871204376,
      "learning_rate": 0.00015662778366914103,
      "loss": 0.5408858299255371,
      "step": 420
    },
    {
      "epoch": 0.6811881188118812,
      "grad_norm": 0.3129599094390869,
      "learning_rate": 0.00015556733828207847,
      "loss": 0.5390897274017334,
      "step": 430
    },
    {
      "epoch": 0.697029702970297,
      "grad_norm": 0.28233346343040466,
      "learning_rate": 0.00015450689289501593,
      "loss": 0.5419738292694092,
      "step": 440
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.21026961505413055,
      "learning_rate": 0.00015344644750795334,
      "loss": 0.5432523727416992,
      "step": 450
    },
    {
      "epoch": 0.7287128712871287,
      "grad_norm": 0.1969085931777954,
      "learning_rate": 0.00015238600212089077,
      "loss": 0.5586908340454102,
      "step": 460
    },
    {
      "epoch": 0.7445544554455445,
      "grad_norm": 0.24481482803821564,
      "learning_rate": 0.00015132555673382823,
      "loss": 0.5176334857940674,
      "step": 470
    },
    {
      "epoch": 0.7603960396039604,
      "grad_norm": 0.2514127194881439,
      "learning_rate": 0.00015026511134676564,
      "loss": 0.5458994388580323,
      "step": 480
    },
    {
      "epoch": 0.7762376237623763,
      "grad_norm": 0.290608286857605,
      "learning_rate": 0.00014920466595970308,
      "loss": 0.5448351383209229,
      "step": 490
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.22577252984046936,
      "learning_rate": 0.0001481442205726405,
      "loss": 0.5721570491790772,
      "step": 500
    },
    {
      "epoch": 0.807920792079208,
      "grad_norm": 0.23058907687664032,
      "learning_rate": 0.00014708377518557795,
      "loss": 0.5574183940887452,
      "step": 510
    },
    {
      "epoch": 0.8237623762376237,
      "grad_norm": 0.1983114629983902,
      "learning_rate": 0.00014602332979851538,
      "loss": 0.540287446975708,
      "step": 520
    },
    {
      "epoch": 0.8396039603960396,
      "grad_norm": 0.2218492478132248,
      "learning_rate": 0.00014496288441145282,
      "loss": 0.5182662963867187,
      "step": 530
    },
    {
      "epoch": 0.8554455445544554,
      "grad_norm": 0.24610327184200287,
      "learning_rate": 0.00014390243902439025,
      "loss": 0.5651758193969727,
      "step": 540
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.22517655789852142,
      "learning_rate": 0.0001428419936373277,
      "loss": 0.5164387226104736,
      "step": 550
    },
    {
      "epoch": 0.8871287128712871,
      "grad_norm": 0.2436833679676056,
      "learning_rate": 0.00014178154825026512,
      "loss": 0.5450125217437745,
      "step": 560
    },
    {
      "epoch": 0.902970297029703,
      "grad_norm": 0.24090257287025452,
      "learning_rate": 0.00014072110286320256,
      "loss": 0.5317369937896729,
      "step": 570
    },
    {
      "epoch": 0.9188118811881189,
      "grad_norm": 0.25686290860176086,
      "learning_rate": 0.00013966065747614,
      "loss": 0.5516084671020508,
      "step": 580
    },
    {
      "epoch": 0.9346534653465347,
      "grad_norm": 0.23638945817947388,
      "learning_rate": 0.0001386002120890774,
      "loss": 0.514578914642334,
      "step": 590
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.23559114336967468,
      "learning_rate": 0.00013753976670201484,
      "loss": 0.5437835693359375,
      "step": 600
    },
    {
      "epoch": 0.9663366336633663,
      "grad_norm": 0.27141445875167847,
      "learning_rate": 0.0001364793213149523,
      "loss": 0.555320930480957,
      "step": 610
    },
    {
      "epoch": 0.9821782178217822,
      "grad_norm": 0.21413768827915192,
      "learning_rate": 0.0001354188759278897,
      "loss": 0.5468743324279786,
      "step": 620
    },
    {
      "epoch": 0.998019801980198,
      "grad_norm": 0.2012445032596588,
      "learning_rate": 0.00013435843054082714,
      "loss": 0.5468167781829834,
      "step": 630
    },
    {
      "epoch": 1.0126732673267327,
      "grad_norm": 0.1769125610589981,
      "learning_rate": 0.0001332979851537646,
      "loss": 0.5139318466186523,
      "step": 640
    },
    {
      "epoch": 1.0285148514851485,
      "grad_norm": 0.2236032634973526,
      "learning_rate": 0.000132237539766702,
      "loss": 0.533442497253418,
      "step": 650
    }
  ],
  "logging_steps": 10,
  "max_steps": 1896,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.293370053971968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}