{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.82648401826484,
  "eval_steps": 0,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 1.210837721824646,
      "learning_rate": 8.384962462644227e-05,
      "loss": 4.3885,
      "step": 10
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.05364489555358887,
      "learning_rate": 9.403937698096759e-05,
      "loss": 0.0377,
      "step": 20
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.05466941371560097,
      "learning_rate": 0.0001,
      "loss": 0.0304,
      "step": 30
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.05443768575787544,
      "learning_rate": 0.0001,
      "loss": 0.0286,
      "step": 40
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.04316823184490204,
      "learning_rate": 0.0001,
      "loss": 0.0269,
      "step": 50
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.040838971734046936,
      "learning_rate": 0.0001,
      "loss": 0.0253,
      "step": 60
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 0.033302322030067444,
      "learning_rate": 0.0001,
      "loss": 0.0246,
      "step": 70
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.033719729632139206,
      "learning_rate": 0.0001,
      "loss": 0.0236,
      "step": 80
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.035154491662979126,
      "learning_rate": 0.0001,
      "loss": 0.0225,
      "step": 90
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.04473581910133362,
      "learning_rate": 0.0001,
      "loss": 0.0215,
      "step": 100
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 0.03445715084671974,
      "learning_rate": 0.0001,
      "loss": 0.0206,
      "step": 110
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.038836944848299026,
      "learning_rate": 0.0001,
      "loss": 0.0192,
      "step": 120
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 0.03825332224369049,
      "learning_rate": 0.0001,
      "loss": 0.0175,
      "step": 130
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 0.06607168912887573,
      "learning_rate": 0.0001,
      "loss": 0.0163,
      "step": 140
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.06894340366125107,
      "learning_rate": 0.0001,
      "loss": 0.0145,
      "step": 150
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.05710868164896965,
      "learning_rate": 0.0001,
      "loss": 0.0135,
      "step": 160
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 0.21631816029548645,
      "learning_rate": 0.0001,
      "loss": 0.0124,
      "step": 170
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.02653978019952774,
      "learning_rate": 0.0001,
      "loss": 0.0108,
      "step": 180
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 0.02567458152770996,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 190
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.02634381130337715,
      "learning_rate": 0.0001,
      "loss": 0.009,
      "step": 200
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.0267449039965868,
      "learning_rate": 0.0001,
      "loss": 0.0082,
      "step": 210
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 0.021301211789250374,
      "learning_rate": 0.0001,
      "loss": 0.0074,
      "step": 220
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 0.019044479355216026,
      "learning_rate": 0.0001,
      "loss": 0.0065,
      "step": 230
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.029325349256396294,
      "learning_rate": 0.0001,
      "loss": 0.0058,
      "step": 240
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.020611237734556198,
      "learning_rate": 0.0001,
      "loss": 0.005,
      "step": 250
    },
    {
      "epoch": 0.4748858447488584,
      "grad_norm": 0.013526758179068565,
      "learning_rate": 0.0001,
      "loss": 0.0048,
      "step": 260
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.013649986125528812,
      "learning_rate": 0.0001,
      "loss": 0.0044,
      "step": 270
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 0.010144168511033058,
      "learning_rate": 0.0001,
      "loss": 0.0039,
      "step": 280
    },
    {
      "epoch": 0.5296803652968036,
      "grad_norm": 0.010870883241295815,
      "learning_rate": 0.0001,
      "loss": 0.0037,
      "step": 290
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.013004078529775143,
      "learning_rate": 0.0001,
      "loss": 0.0035,
      "step": 300
    },
    {
      "epoch": 0.5662100456621004,
      "grad_norm": 0.011805733665823936,
      "learning_rate": 0.0001,
      "loss": 0.0032,
      "step": 310
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 0.009305172599852085,
      "learning_rate": 0.0001,
      "loss": 0.0032,
      "step": 320
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.010236217640340328,
      "learning_rate": 0.0001,
      "loss": 0.0032,
      "step": 330
    },
    {
      "epoch": 0.6210045662100456,
      "grad_norm": 0.006890588905662298,
      "learning_rate": 0.0001,
      "loss": 0.0029,
      "step": 340
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.009779484011232853,
      "learning_rate": 0.0001,
      "loss": 0.0029,
      "step": 350
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.00785751547664404,
      "learning_rate": 0.0001,
      "loss": 0.0028,
      "step": 360
    },
    {
      "epoch": 0.6757990867579908,
      "grad_norm": 0.0072973244823515415,
      "learning_rate": 0.0001,
      "loss": 0.0029,
      "step": 370
    },
    {
      "epoch": 0.6940639269406392,
      "grad_norm": 0.007814369164407253,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 380
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.009240522980690002,
      "learning_rate": 0.0001,
      "loss": 0.0027,
      "step": 390
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.009443056769669056,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 400
    },
    {
      "epoch": 0.7488584474885844,
      "grad_norm": 0.007976274006068707,
      "learning_rate": 0.0001,
      "loss": 0.0025,
      "step": 410
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.007670409046113491,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 420
    },
    {
      "epoch": 0.7853881278538812,
      "grad_norm": 0.007698874454945326,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 430
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 0.0064626955427229404,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 440
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.00718158483505249,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 450
    },
    {
      "epoch": 0.8401826484018264,
      "grad_norm": 0.00720883859321475,
      "learning_rate": 0.0001,
      "loss": 0.0024,
      "step": 460
    },
    {
      "epoch": 0.8584474885844748,
      "grad_norm": 0.0070312367752194405,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 470
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.006656646262854338,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 480
    },
    {
      "epoch": 0.8949771689497716,
      "grad_norm": 0.005672188475728035,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 490
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.006890942342579365,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 500
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.007466984912753105,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 510
    },
    {
      "epoch": 0.9497716894977168,
      "grad_norm": 0.004908357746899128,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 520
    },
    {
      "epoch": 0.9680365296803652,
      "grad_norm": 0.006489965599030256,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 530
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.004896162543445826,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 540
    },
    {
      "epoch": 1.004566210045662,
      "grad_norm": 0.006576609797775745,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 550
    },
    {
      "epoch": 1.0228310502283104,
      "grad_norm": 0.005738385953009129,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 560
    },
    {
      "epoch": 1.0410958904109588,
      "grad_norm": 0.004859850741922855,
      "learning_rate": 0.0001,
      "loss": 0.0021,
      "step": 570
    },
    {
      "epoch": 1.0593607305936072,
      "grad_norm": 0.0058967191725969315,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 580
    },
    {
      "epoch": 1.0776255707762556,
      "grad_norm": 0.006550053600221872,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 590
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.005125932861119509,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 600
    },
    {
      "epoch": 1.1141552511415524,
      "grad_norm": 0.006288828328251839,
      "learning_rate": 0.0001,
      "loss": 0.0021,
      "step": 610
    },
    {
      "epoch": 1.1324200913242009,
      "grad_norm": 0.005583199672400951,
      "learning_rate": 0.0001,
      "loss": 0.0021,
      "step": 620
    },
    {
      "epoch": 1.1506849315068493,
      "grad_norm": 0.009129468351602554,
      "learning_rate": 0.0001,
      "loss": 0.0021,
      "step": 630
    },
    {
      "epoch": 1.1689497716894977,
      "grad_norm": 0.007402694784104824,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 640
    },
    {
      "epoch": 1.187214611872146,
      "grad_norm": 0.006056242622435093,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 650
    },
    {
      "epoch": 1.2054794520547945,
      "grad_norm": 0.006746839266270399,
      "learning_rate": 0.0001,
      "loss": 0.0021,
      "step": 660
    },
    {
      "epoch": 1.2237442922374429,
      "grad_norm": 0.005732604302465916,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 670
    },
    {
      "epoch": 1.2420091324200913,
      "grad_norm": 0.005662497598677874,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 680
    },
    {
      "epoch": 1.2602739726027397,
      "grad_norm": 0.005395127926021814,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 690
    },
    {
      "epoch": 1.278538812785388,
      "grad_norm": 0.006477879825979471,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 700
    },
    {
      "epoch": 1.2968036529680365,
      "grad_norm": 0.00455828383564949,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 710
    },
    {
      "epoch": 1.3150684931506849,
      "grad_norm": 0.006546813528984785,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 720
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.004749835003167391,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 730
    },
    {
      "epoch": 1.3515981735159817,
      "grad_norm": 0.0060322824865579605,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 740
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.004833315033465624,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 750
    },
    {
      "epoch": 1.3881278538812785,
      "grad_norm": 0.006321150343865156,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 760
    },
    {
      "epoch": 1.4063926940639269,
      "grad_norm": 0.00560184707865119,
      "learning_rate": 0.0001,
      "loss": 0.002,
      "step": 770
    },
    {
      "epoch": 1.4246575342465753,
      "grad_norm": 0.005110142752528191,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 780
    },
    {
      "epoch": 1.4429223744292237,
      "grad_norm": 0.005219564773142338,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 790
    },
    {
      "epoch": 1.461187214611872,
      "grad_norm": 0.004923923406749964,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 800
    },
    {
      "epoch": 1.4794520547945205,
      "grad_norm": 0.004175902344286442,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 810
    },
    {
      "epoch": 1.4977168949771689,
      "grad_norm": 0.005314885172992945,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 820
    },
    {
      "epoch": 1.5159817351598175,
      "grad_norm": 0.004691184964030981,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 830
    },
    {
      "epoch": 1.5342465753424657,
      "grad_norm": 0.006277224514633417,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 840
    },
    {
      "epoch": 1.5525114155251143,
      "grad_norm": 0.004492647014558315,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 850
    },
    {
      "epoch": 1.5707762557077625,
      "grad_norm": 0.00427781417965889,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 860
    },
    {
      "epoch": 1.589041095890411,
      "grad_norm": 0.005225111730396748,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 870
    },
    {
      "epoch": 1.6073059360730593,
      "grad_norm": 0.004722876939922571,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 880
    },
    {
      "epoch": 1.625570776255708,
      "grad_norm": 0.0056340452283620834,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 890
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.004999073222279549,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 900
    },
    {
      "epoch": 1.6621004566210047,
      "grad_norm": 0.005323594436049461,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 910
    },
    {
      "epoch": 1.6803652968036529,
      "grad_norm": 0.006069580093026161,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 920
    },
    {
      "epoch": 1.6986301369863015,
      "grad_norm": 0.006003932561725378,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 930
    },
    {
      "epoch": 1.7168949771689497,
      "grad_norm": 0.005637574940919876,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 940
    },
    {
      "epoch": 1.7351598173515983,
      "grad_norm": 0.004971097223460674,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 950
    },
    {
      "epoch": 1.7534246575342465,
      "grad_norm": 0.005295970477163792,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 960
    },
    {
      "epoch": 1.771689497716895,
      "grad_norm": 0.0048394943587481976,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 970
    },
    {
      "epoch": 1.7899543378995433,
      "grad_norm": 0.005681538488715887,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 980
    },
    {
      "epoch": 1.808219178082192,
      "grad_norm": 0.007275606505572796,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 990
    },
    {
      "epoch": 1.82648401826484,
      "grad_norm": 0.004521261900663376,
      "learning_rate": 0.0001,
      "loss": 0.0016,
      "step": 1000
    },
    {
      "epoch": 1.82648401826484,
      "step": 1000,
      "total_flos": 5.565784553370419e+18,
      "train_loss": 0.04975467654503882,
      "train_runtime": 15752.6954,
      "train_samples_per_second": 10.157,
      "train_steps_per_second": 0.063
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.565784553370419e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}