{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 532,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037638202775817454,
      "grad_norm": 13.610795098502107,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.5914,
      "step": 10
    },
    {
      "epoch": 0.07527640555163491,
      "grad_norm": 0.9699645754094162,
      "learning_rate": 1.7592592592592594e-06,
      "loss": 0.5843,
      "step": 20
    },
    {
      "epoch": 0.11291460832745237,
      "grad_norm": 0.5845916009861534,
      "learning_rate": 2.6851851851851856e-06,
      "loss": 0.5781,
      "step": 30
    },
    {
      "epoch": 0.15055281110326982,
      "grad_norm": 0.5917279916406908,
      "learning_rate": 3.6111111111111115e-06,
      "loss": 0.5653,
      "step": 40
    },
    {
      "epoch": 0.18819101387908727,
      "grad_norm": 0.5696097079287838,
      "learning_rate": 4.537037037037038e-06,
      "loss": 0.5927,
      "step": 50
    },
    {
      "epoch": 0.22582921665490474,
      "grad_norm": 0.5761389794818529,
      "learning_rate": 4.998650245168965e-06,
      "loss": 0.5859,
      "step": 60
    },
    {
      "epoch": 0.26346741943072216,
      "grad_norm": 0.576477237978447,
      "learning_rate": 4.987860949769804e-06,
      "loss": 0.582,
      "step": 70
    },
    {
      "epoch": 0.30110562220653964,
      "grad_norm": 0.556511371295206,
      "learning_rate": 4.9663289476829e-06,
      "loss": 0.5712,
      "step": 80
    },
    {
      "epoch": 0.3387438249823571,
      "grad_norm": 0.47938070366971103,
      "learning_rate": 4.934147215158732e-06,
      "loss": 0.5614,
      "step": 90
    },
    {
      "epoch": 0.37638202775817453,
      "grad_norm": 0.41700685090674505,
      "learning_rate": 4.891454714510784e-06,
      "loss": 0.6062,
      "step": 100
    },
    {
      "epoch": 0.414020230533992,
      "grad_norm": 0.4084825379730698,
      "learning_rate": 4.838435794069406e-06,
      "loss": 0.5703,
      "step": 110
    },
    {
      "epoch": 0.4516584333098095,
      "grad_norm": 0.4167412677659701,
      "learning_rate": 4.775319392156593e-06,
      "loss": 0.5933,
      "step": 120
    },
    {
      "epoch": 0.4892966360856269,
      "grad_norm": 0.4066934770436394,
      "learning_rate": 4.70237804851899e-06,
      "loss": 0.5457,
      "step": 130
    },
    {
      "epoch": 0.5269348388614443,
      "grad_norm": 0.39475972226137096,
      "learning_rate": 4.619926727487774e-06,
      "loss": 0.5797,
      "step": 140
    },
    {
      "epoch": 0.5645730416372619,
      "grad_norm": 0.42220410240509404,
      "learning_rate": 4.528321457947091e-06,
      "loss": 0.5977,
      "step": 150
    },
    {
      "epoch": 0.6022112444130793,
      "grad_norm": 0.3914884231722468,
      "learning_rate": 4.427957795983715e-06,
      "loss": 0.5789,
      "step": 160
    },
    {
      "epoch": 0.6398494471888967,
      "grad_norm": 0.40266440109112717,
      "learning_rate": 4.319269116856291e-06,
      "loss": 0.5716,
      "step": 170
    },
    {
      "epoch": 0.6774876499647142,
      "grad_norm": 0.41129740802214726,
      "learning_rate": 4.2027247436595245e-06,
      "loss": 0.5597,
      "step": 180
    },
    {
      "epoch": 0.7151258527405316,
      "grad_norm": 0.4686973204175566,
      "learning_rate": 4.078827920763835e-06,
      "loss": 0.5803,
      "step": 190
    },
    {
      "epoch": 0.7527640555163491,
      "grad_norm": 0.38540729078595337,
      "learning_rate": 3.948113640781265e-06,
      "loss": 0.5723,
      "step": 200
    },
    {
      "epoch": 0.7904022582921666,
      "grad_norm": 0.40445228822396667,
      "learning_rate": 3.8111463344409026e-06,
      "loss": 0.561,
      "step": 210
    },
    {
      "epoch": 0.828040461067984,
      "grad_norm": 0.4653487942714477,
      "learning_rate": 3.668517433349069e-06,
      "loss": 0.5807,
      "step": 220
    },
    {
      "epoch": 0.8656786638438014,
      "grad_norm": 0.4241292760945627,
      "learning_rate": 3.520842816158374e-06,
      "loss": 0.5889,
      "step": 230
    },
    {
      "epoch": 0.903316866619619,
      "grad_norm": 0.4124860362346966,
      "learning_rate": 3.368760149173219e-06,
      "loss": 0.5976,
      "step": 240
    },
    {
      "epoch": 0.9409550693954364,
      "grad_norm": 0.40795355323908694,
      "learning_rate": 3.212926132875141e-06,
      "loss": 0.5658,
      "step": 250
    },
    {
      "epoch": 0.9785932721712538,
      "grad_norm": 0.41045446321734286,
      "learning_rate": 3.054013666257638e-06,
      "loss": 0.5814,
      "step": 260
    },
    {
      "epoch": 1.015055281110327,
      "grad_norm": 0.4409995582342298,
      "learning_rate": 2.8927089412150176e-06,
      "loss": 0.5907,
      "step": 270
    },
    {
      "epoch": 1.0526934838861444,
      "grad_norm": 0.4043201145148639,
      "learning_rate": 2.729708479531844e-06,
      "loss": 0.5346,
      "step": 280
    },
    {
      "epoch": 1.090331686661962,
      "grad_norm": 0.3985913687368217,
      "learning_rate": 2.5657161252674047e-06,
      "loss": 0.535,
      "step": 290
    },
    {
      "epoch": 1.1279698894377794,
      "grad_norm": 0.3946559086316167,
      "learning_rate": 2.4014400055222337e-06,
      "loss": 0.5177,
      "step": 300
    },
    {
      "epoch": 1.1656080922135967,
      "grad_norm": 0.42945485549653484,
      "learning_rate": 2.2375894727102552e-06,
      "loss": 0.553,
      "step": 310
    },
    {
      "epoch": 1.2032462949894143,
      "grad_norm": 0.39437996434435546,
      "learning_rate": 2.0748720415399542e-06,
      "loss": 0.5312,
      "step": 320
    },
    {
      "epoch": 1.2408844977652318,
      "grad_norm": 0.3716214397572245,
      "learning_rate": 1.913990333930858e-06,
      "loss": 0.5286,
      "step": 330
    },
    {
      "epoch": 1.278522700541049,
      "grad_norm": 0.40068573317589684,
      "learning_rate": 1.7556390450573213e-06,
      "loss": 0.5362,
      "step": 340
    },
    {
      "epoch": 1.3161609033168666,
      "grad_norm": 0.3616596747761561,
      "learning_rate": 1.600501943620384e-06,
      "loss": 0.5286,
      "step": 350
    },
    {
      "epoch": 1.353799106092684,
      "grad_norm": 0.38779033566892823,
      "learning_rate": 1.4492489193006884e-06,
      "loss": 0.5263,
      "step": 360
    },
    {
      "epoch": 1.3914373088685015,
      "grad_norm": 0.3757853739580612,
      "learning_rate": 1.302533090141689e-06,
      "loss": 0.516,
      "step": 370
    },
    {
      "epoch": 1.429075511644319,
      "grad_norm": 0.38727201501707054,
      "learning_rate": 1.1609879823536233e-06,
      "loss": 0.5416,
      "step": 380
    },
    {
      "epoch": 1.4667137144201363,
      "grad_norm": 0.41256807796835565,
      "learning_rate": 1.0252247947159846e-06,
      "loss": 0.5489,
      "step": 390
    },
    {
      "epoch": 1.5043519171959538,
      "grad_norm": 0.3710868452573983,
      "learning_rate": 8.95829759390954e-07,
      "loss": 0.545,
      "step": 400
    },
    {
      "epoch": 1.5419901199717714,
      "grad_norm": 0.3694905808253818,
      "learning_rate": 7.733616105439077e-07,
      "loss": 0.5208,
      "step": 410
    },
    {
      "epoch": 1.5796283227475887,
      "grad_norm": 0.3615477041656024,
      "learning_rate": 6.58349171701651e-07,
      "loss": 0.5237,
      "step": 420
    },
    {
      "epoch": 1.6172665255234062,
      "grad_norm": 0.3804185781850594,
      "learning_rate": 5.51289072266255e-07,
      "loss": 0.5608,
      "step": 430
    },
    {
      "epoch": 1.6549047282992237,
      "grad_norm": 0.40468195026925746,
      "learning_rate": 4.5264360304473065e-07,
      "loss": 0.5576,
      "step": 440
    },
    {
      "epoch": 1.692542931075041,
      "grad_norm": 0.367137564529641,
      "learning_rate": 3.6283872005444087e-07,
      "loss": 0.5312,
      "step": 450
    },
    {
      "epoch": 1.7301811338508586,
      "grad_norm": 0.3963215645004468,
      "learning_rate": 2.8226220522394735e-07,
      "loss": 0.5362,
      "step": 460
    },
    {
      "epoch": 1.7678193366266761,
      "grad_norm": 0.38136903383145776,
      "learning_rate": 2.1126199193144904e-07,
      "loss": 0.558,
      "step": 470
    },
    {
      "epoch": 1.8054575394024934,
      "grad_norm": 0.38938465164870284,
      "learning_rate": 1.5014466261124128e-07,
      "loss": 0.5114,
      "step": 480
    },
    {
      "epoch": 1.843095742178311,
      "grad_norm": 0.37548505603471355,
      "learning_rate": 9.917412491559337e-08,
      "loss": 0.5402,
      "step": 490
    },
    {
      "epoch": 1.8807339449541285,
      "grad_norm": 0.3575809194576506,
      "learning_rate": 5.8570472148445633e-08,
      "loss": 0.5349,
      "step": 500
    },
    {
      "epoch": 1.9183721477299458,
      "grad_norm": 0.3899130339561275,
      "learning_rate": 2.8509032891635146e-08,
      "loss": 0.5419,
      "step": 510
    },
    {
      "epoch": 1.9560103505057633,
      "grad_norm": 0.4032737933879565,
      "learning_rate": 9.119613927399684e-09,
      "loss": 0.5312,
      "step": 520
    },
    {
      "epoch": 1.9936485532815809,
      "grad_norm": 0.3608459597802774,
      "learning_rate": 4.859397262726995e-10,
      "loss": 0.5583,
      "step": 530
    },
    {
      "epoch": 2.0,
      "step": 532,
      "total_flos": 8.119097669378376e+17,
      "train_loss": 0.558736775154458,
      "train_runtime": 23106.9266,
      "train_samples_per_second": 11.774,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 10,
  "max_steps": 532,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.119097669378376e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}