{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013348907058234607,
      "grad_norm": 74.82529080509352,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.6277,
      "step": 10
    },
    {
      "epoch": 0.026697814116469213,
      "grad_norm": 1.6096919343173548,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 0.6328,
      "step": 20
    },
    {
      "epoch": 0.04004672117470382,
      "grad_norm": 0.9314352408083703,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 0.6041,
      "step": 30
    },
    {
      "epoch": 0.053395628232938426,
      "grad_norm": 0.811733547929806,
      "learning_rate": 2.6e-06,
      "loss": 0.6042,
      "step": 40
    },
    {
      "epoch": 0.06674453529117304,
      "grad_norm": 0.7093539476838706,
      "learning_rate": 3.266666666666667e-06,
      "loss": 0.603,
      "step": 50
    },
    {
      "epoch": 0.08009344234940764,
      "grad_norm": 0.7170335789165264,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 0.6155,
      "step": 60
    },
    {
      "epoch": 0.09344234940764225,
      "grad_norm": 0.6815670283453077,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.6002,
      "step": 70
    },
    {
      "epoch": 0.10679125646587685,
      "grad_norm": 0.656703252575977,
      "learning_rate": 4.99956677884892e-06,
      "loss": 0.61,
      "step": 80
    },
    {
      "epoch": 0.12014016352411146,
      "grad_norm": 0.5920011648125949,
      "learning_rate": 4.994694765050121e-06,
      "loss": 0.6102,
      "step": 90
    },
    {
      "epoch": 0.13348907058234608,
      "grad_norm": 0.5227326374455843,
      "learning_rate": 4.984419797901491e-06,
      "loss": 0.6009,
      "step": 100
    },
    {
      "epoch": 0.14683797764058068,
      "grad_norm": 0.5495253836256794,
      "learning_rate": 4.9687641306938766e-06,
      "loss": 0.5938,
      "step": 110
    },
    {
      "epoch": 0.16018688469881529,
      "grad_norm": 0.48232788709453134,
      "learning_rate": 4.94776167011629e-06,
      "loss": 0.5871,
      "step": 120
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 0.506411321536645,
      "learning_rate": 4.921457902821578e-06,
      "loss": 0.5974,
      "step": 130
    },
    {
      "epoch": 0.1868846988152845,
      "grad_norm": 0.4596419488812572,
      "learning_rate": 4.889909796912454e-06,
      "loss": 0.5867,
      "step": 140
    },
    {
      "epoch": 0.2002336058735191,
      "grad_norm": 0.4945179863512727,
      "learning_rate": 4.85318567856128e-06,
      "loss": 0.5829,
      "step": 150
    },
    {
      "epoch": 0.2135825129317537,
      "grad_norm": 0.48473847553604443,
      "learning_rate": 4.811365084030784e-06,
      "loss": 0.59,
      "step": 160
    },
    {
      "epoch": 0.2269314199899883,
      "grad_norm": 0.5177422654479074,
      "learning_rate": 4.764538587416233e-06,
      "loss": 0.5961,
      "step": 170
    },
    {
      "epoch": 0.2402803270482229,
      "grad_norm": 0.5448020887198345,
      "learning_rate": 4.712807604482108e-06,
      "loss": 0.5687,
      "step": 180
    },
    {
      "epoch": 0.25362923410645755,
      "grad_norm": 0.4464063495342875,
      "learning_rate": 4.656284173018144e-06,
      "loss": 0.5858,
      "step": 190
    },
    {
      "epoch": 0.26697814116469215,
      "grad_norm": 0.45099478856513986,
      "learning_rate": 4.595090710190419e-06,
      "loss": 0.6043,
      "step": 200
    },
    {
      "epoch": 0.28032704822292676,
      "grad_norm": 0.44848286804261916,
      "learning_rate": 4.529359747413038e-06,
      "loss": 0.591,
      "step": 210
    },
    {
      "epoch": 0.29367595528116136,
      "grad_norm": 0.4411730495621085,
      "learning_rate": 4.4592336433146e-06,
      "loss": 0.5944,
      "step": 220
    },
    {
      "epoch": 0.30702486233939597,
      "grad_norm": 0.48448789063177666,
      "learning_rate": 4.384864275421109e-06,
      "loss": 0.5999,
      "step": 230
    },
    {
      "epoch": 0.32037376939763057,
      "grad_norm": 0.444274267493019,
      "learning_rate": 4.30641271122307e-06,
      "loss": 0.6094,
      "step": 240
    },
    {
      "epoch": 0.3337226764558652,
      "grad_norm": 0.4863069333544111,
      "learning_rate": 4.224048859339175e-06,
      "loss": 0.6174,
      "step": 250
    },
    {
      "epoch": 0.3470715835140998,
      "grad_norm": 0.45811760037842997,
      "learning_rate": 4.1379511015320625e-06,
      "loss": 0.6011,
      "step": 260
    },
    {
      "epoch": 0.3604204905723344,
      "grad_norm": 0.4519496506749116,
      "learning_rate": 4.048305906373151e-06,
      "loss": 0.6139,
      "step": 270
    },
    {
      "epoch": 0.373769397630569,
      "grad_norm": 0.46096665359482364,
      "learning_rate": 3.955307425393224e-06,
      "loss": 0.5747,
      "step": 280
    },
    {
      "epoch": 0.3871183046888036,
      "grad_norm": 0.43711465245434705,
      "learning_rate": 3.859157072593459e-06,
      "loss": 0.5878,
      "step": 290
    },
    {
      "epoch": 0.4004672117470382,
      "grad_norm": 0.4882102831091009,
      "learning_rate": 3.760063088227542e-06,
      "loss": 0.6029,
      "step": 300
    },
    {
      "epoch": 0.4138161188052728,
      "grad_norm": 0.4342997927660038,
      "learning_rate": 3.658240087799655e-06,
      "loss": 0.5778,
      "step": 310
    },
    {
      "epoch": 0.4271650258635074,
      "grad_norm": 0.43187112453168347,
      "learning_rate": 3.5539085972550786e-06,
      "loss": 0.5992,
      "step": 320
    },
    {
      "epoch": 0.440513932921742,
      "grad_norm": 0.471747382817541,
      "learning_rate": 3.4472945753701038e-06,
      "loss": 0.5953,
      "step": 330
    },
    {
      "epoch": 0.4538628399799766,
      "grad_norm": 0.44915302997798534,
      "learning_rate": 3.338628924375638e-06,
      "loss": 0.5794,
      "step": 340
    },
    {
      "epoch": 0.4672117470382112,
      "grad_norm": 0.4619611771891075,
      "learning_rate": 3.228146989874389e-06,
      "loss": 0.5877,
      "step": 350
    },
    {
      "epoch": 0.4805606540964458,
      "grad_norm": 0.4885767281577149,
      "learning_rate": 3.116088051134695e-06,
      "loss": 0.5849,
      "step": 360
    },
    {
      "epoch": 0.4939095611546805,
      "grad_norm": 0.46385582406105635,
      "learning_rate": 3.002694802864912e-06,
      "loss": 0.6113,
      "step": 370
    },
    {
      "epoch": 0.5072584682129151,
      "grad_norm": 0.4631046992756232,
      "learning_rate": 2.888212829590719e-06,
      "loss": 0.6048,
      "step": 380
    },
    {
      "epoch": 0.5206073752711496,
      "grad_norm": 0.43044083063105687,
      "learning_rate": 2.77289007377372e-06,
      "loss": 0.5776,
      "step": 390
    },
    {
      "epoch": 0.5339562823293843,
      "grad_norm": 0.48516134620233986,
      "learning_rate": 2.6569762988232838e-06,
      "loss": 0.604,
      "step": 400
    },
    {
      "epoch": 0.5473051893876189,
      "grad_norm": 0.4819838364354133,
      "learning_rate": 2.5407225481646146e-06,
      "loss": 0.5734,
      "step": 410
    },
    {
      "epoch": 0.5606540964458535,
      "grad_norm": 0.4651999207262788,
      "learning_rate": 2.4243806015345988e-06,
      "loss": 0.5838,
      "step": 420
    },
    {
      "epoch": 0.5740030035040881,
      "grad_norm": 0.4376372826414532,
      "learning_rate": 2.3082024296829538e-06,
      "loss": 0.5692,
      "step": 430
    },
    {
      "epoch": 0.5873519105623227,
      "grad_norm": 0.45235705289954437,
      "learning_rate": 2.192439648659699e-06,
      "loss": 0.5807,
      "step": 440
    },
    {
      "epoch": 0.6007008176205573,
      "grad_norm": 0.4787657223646769,
      "learning_rate": 2.0773429748708153e-06,
      "loss": 0.5954,
      "step": 450
    },
    {
      "epoch": 0.6140497246787919,
      "grad_norm": 0.4533551445182391,
      "learning_rate": 1.963161682082342e-06,
      "loss": 0.5884,
      "step": 460
    },
    {
      "epoch": 0.6273986317370265,
      "grad_norm": 0.4272140082533887,
      "learning_rate": 1.850143061548907e-06,
      "loss": 0.5823,
      "step": 470
    },
    {
      "epoch": 0.6407475387952611,
      "grad_norm": 0.4392811733084597,
      "learning_rate": 1.7385318864359304e-06,
      "loss": 0.5881,
      "step": 480
    },
    {
      "epoch": 0.6540964458534958,
      "grad_norm": 0.45353341871174696,
      "learning_rate": 1.6285698816954626e-06,
      "loss": 0.5975,
      "step": 490
    },
    {
      "epoch": 0.6674453529117303,
      "grad_norm": 0.4996106273981709,
      "learning_rate": 1.520495200543754e-06,
      "loss": 0.5933,
      "step": 500
    },
    {
      "epoch": 0.680794259969965,
      "grad_norm": 0.4365504487522075,
      "learning_rate": 1.41454190867443e-06,
      "loss": 0.5967,
      "step": 510
    },
    {
      "epoch": 0.6941431670281996,
      "grad_norm": 0.44793327079373074,
      "learning_rate": 1.3109394773243117e-06,
      "loss": 0.5848,
      "step": 520
    },
    {
      "epoch": 0.7074920740864342,
      "grad_norm": 0.42862128316402553,
      "learning_rate": 1.2099122862898214e-06,
      "loss": 0.6007,
      "step": 530
    },
    {
      "epoch": 0.7208409811446688,
      "grad_norm": 0.432473388398012,
      "learning_rate": 1.1116791379703032e-06,
      "loss": 0.6002,
      "step": 540
    },
    {
      "epoch": 0.7341898882029034,
      "grad_norm": 0.4365401035182129,
      "learning_rate": 1.0164527834907468e-06,
      "loss": 0.5881,
      "step": 550
    },
    {
      "epoch": 0.747538795261138,
      "grad_norm": 0.44113418564253065,
      "learning_rate": 9.244394619302338e-07,
      "loss": 0.5681,
      "step": 560
    },
    {
      "epoch": 0.7608877023193726,
      "grad_norm": 0.4530120280115404,
      "learning_rate": 8.35838453654009e-07,
      "loss": 0.6012,
      "step": 570
    },
    {
      "epoch": 0.7742366093776072,
      "grad_norm": 0.43315844481160726,
      "learning_rate": 7.508416487165862e-07,
      "loss": 0.5864,
      "step": 580
    },
    {
      "epoch": 0.7875855164358418,
      "grad_norm": 0.43418599980747014,
      "learning_rate": 6.696331312706245e-07,
      "loss": 0.573,
      "step": 590
    },
    {
      "epoch": 0.8009344234940764,
      "grad_norm": 0.393826774521195,
      "learning_rate": 5.923887808816373e-07,
      "loss": 0.5887,
      "step": 600
    },
    {
      "epoch": 0.8142833305523111,
      "grad_norm": 0.447594763094874,
      "learning_rate": 5.192758916120236e-07,
      "loss": 0.5824,
      "step": 610
    },
    {
      "epoch": 0.8276322376105456,
      "grad_norm": 0.41723158327426507,
      "learning_rate": 4.5045280969937847e-07,
      "loss": 0.5913,
      "step": 620
    },
    {
      "epoch": 0.8409811446687803,
      "grad_norm": 0.42914391176019,
      "learning_rate": 3.86068590613804e-07,
      "loss": 0.5901,
      "step": 630
    },
    {
      "epoch": 0.8543300517270148,
      "grad_norm": 0.42096167751505276,
      "learning_rate": 3.262626762369525e-07,
      "loss": 0.5972,
      "step": 640
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 0.4194093214775328,
      "learning_rate": 2.7116459286195887e-07,
      "loss": 0.6007,
      "step": 650
    },
    {
      "epoch": 0.881027865843484,
      "grad_norm": 0.43327319840700385,
      "learning_rate": 2.208936706683351e-07,
      "loss": 0.5838,
      "step": 660
    },
    {
      "epoch": 0.8943767729017187,
      "grad_norm": 0.4359893596297785,
      "learning_rate": 1.7555878527937164e-07,
      "loss": 0.5914,
      "step": 670
    },
    {
      "epoch": 0.9077256799599532,
      "grad_norm": 0.415818533124484,
      "learning_rate": 1.352581219617824e-07,
      "loss": 0.5777,
      "step": 680
    },
    {
      "epoch": 0.9210745870181879,
      "grad_norm": 0.41684651467396844,
      "learning_rate": 1.0007896297828113e-07,
      "loss": 0.5804,
      "step": 690
    },
    {
      "epoch": 0.9344234940764224,
      "grad_norm": 0.4339073826453879,
      "learning_rate": 7.009749855363457e-08,
      "loss": 0.5962,
      "step": 700
    },
    {
      "epoch": 0.9477724011346571,
      "grad_norm": 0.4254475467695668,
      "learning_rate": 4.537866186360207e-08,
      "loss": 0.5783,
      "step": 710
    },
    {
      "epoch": 0.9611213081928917,
      "grad_norm": 0.43873911481956157,
      "learning_rate": 2.59759884041369e-08,
      "loss": 0.5809,
      "step": 720
    },
    {
      "epoch": 0.9744702152511263,
      "grad_norm": 0.42847736934790803,
      "learning_rate": 1.193150004542204e-08,
      "loss": 0.5988,
      "step": 730
    },
    {
      "epoch": 0.987819122309361,
      "grad_norm": 0.4233057016442379,
      "learning_rate": 3.275614021857609e-09,
      "loss": 0.5788,
      "step": 740
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4142778830762649,
      "learning_rate": 2.7077055103075233e-11,
      "loss": 0.5609,
      "step": 750
    },
    {
      "epoch": 1.0,
      "step": 750,
      "total_flos": 9.236595014945997e+17,
      "train_loss": 0.5925992005666098,
      "train_runtime": 15477.022,
      "train_samples_per_second": 24.78,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.236595014945997e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}