{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.91111111111111,
  "eval_steps": 500,
  "global_step": 896,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.4277842044830322,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.3797,
      "step": 10
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.029878854751587,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.424,
      "step": 20
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.6295349597930908,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.2302,
      "step": 30
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.916685163974762,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.1664,
      "step": 40
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.7659821510314941,
      "learning_rate": 0.000199982965150241,
      "loss": 0.1398,
      "step": 50
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.0613561868667603,
      "learning_rate": 0.00019984672117252423,
      "loss": 0.1207,
      "step": 60
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.7991588711738586,
      "learning_rate": 0.00019957441887293156,
      "loss": 0.1119,
      "step": 70
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.6806069016456604,
      "learning_rate": 0.00019916642931015662,
      "loss": 0.0885,
      "step": 80
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6726401448249817,
      "learning_rate": 0.00019862330844011466,
      "loss": 0.0849,
      "step": 90
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.44822949171066284,
      "learning_rate": 0.00019794579635835704,
      "loss": 0.0721,
      "step": 100
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.40653809905052185,
      "learning_rate": 0.0001971348162915637,
      "loss": 0.0729,
      "step": 110
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.40992143750190735,
      "learning_rate": 0.00019619147333948823,
      "loss": 0.0666,
      "step": 120
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.6051583290100098,
      "learning_rate": 0.00019511705296906945,
      "loss": 0.0606,
      "step": 130
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.46464696526527405,
      "learning_rate": 0.00019391301926276156,
      "loss": 0.0631,
      "step": 140
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.5700137615203857,
      "learning_rate": 0.00019258101292347042,
      "loss": 0.0594,
      "step": 150
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5737802386283875,
      "learning_rate": 0.0001911228490388136,
      "loss": 0.0609,
      "step": 160
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.4904007315635681,
      "learning_rate": 0.0001895405146077514,
      "loss": 0.0539,
      "step": 170
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4444526731967926,
      "learning_rate": 0.00018783616583295943,
      "loss": 0.0514,
      "step": 180
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 0.3706776201725006,
      "learning_rate": 0.00018601212518263156,
      "loss": 0.0495,
      "step": 190
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.29509109258651733,
      "learning_rate": 0.00018407087822571794,
      "loss": 0.0477,
      "step": 200
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.4063428044319153,
      "learning_rate": 0.00018201507024490988,
      "loss": 0.0485,
      "step": 210
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.4438524544239044,
      "learning_rate": 0.0001798475026319875,
      "loss": 0.046,
      "step": 220
    },
    {
      "epoch": 5.111111111111111,
      "grad_norm": 0.26472207903862,
      "learning_rate": 0.000177571129070442,
      "loss": 0.0452,
      "step": 230
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 0.3637102246284485,
      "learning_rate": 0.0001751890515105738,
      "loss": 0.0471,
      "step": 240
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.2891571819782257,
      "learning_rate": 0.00017270451594255233,
      "loss": 0.0436,
      "step": 250
    },
    {
      "epoch": 5.777777777777778,
      "grad_norm": 0.380941778421402,
      "learning_rate": 0.00017012090797319628,
      "loss": 0.0439,
      "step": 260
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.573648989200592,
      "learning_rate": 0.00016744174821250237,
      "loss": 0.0434,
      "step": 270
    },
    {
      "epoch": 6.222222222222222,
      "grad_norm": 0.34533384442329407,
      "learning_rate": 0.0001646706874762089,
      "loss": 0.0369,
      "step": 280
    },
    {
      "epoch": 6.444444444444445,
      "grad_norm": 0.5272351503372192,
      "learning_rate": 0.0001618115018109318,
      "loss": 0.0403,
      "step": 290
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.2849768400192261,
      "learning_rate": 0.00015886808734865202,
      "loss": 0.0388,
      "step": 300
    },
    {
      "epoch": 6.888888888888889,
      "grad_norm": 0.301411896944046,
      "learning_rate": 0.00015584445499756578,
      "loss": 0.0405,
      "step": 310
    },
    {
      "epoch": 7.111111111111111,
      "grad_norm": 0.32372748851776123,
      "learning_rate": 0.0001527447249765329,
      "loss": 0.0362,
      "step": 320
    },
    {
      "epoch": 7.333333333333333,
      "grad_norm": 0.26995155215263367,
      "learning_rate": 0.00014957312120057005,
      "loss": 0.0335,
      "step": 330
    },
    {
      "epoch": 7.555555555555555,
      "grad_norm": 0.35481250286102295,
      "learning_rate": 0.00014633396552504063,
      "loss": 0.0424,
      "step": 340
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.3813558518886566,
      "learning_rate": 0.00014303167185638366,
      "loss": 0.0378,
      "step": 350
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.3790789842605591,
      "learning_rate": 0.0001396707401374078,
      "loss": 0.0403,
      "step": 360
    },
    {
      "epoch": 8.222222222222221,
      "grad_norm": 0.28233516216278076,
      "learning_rate": 0.00013625575021534536,
      "loss": 0.0304,
      "step": 370
    },
    {
      "epoch": 8.444444444444445,
      "grad_norm": 0.4000020921230316,
      "learning_rate": 0.00013279135560102337,
      "loss": 0.033,
      "step": 380
    },
    {
      "epoch": 8.666666666666666,
      "grad_norm": 0.29253950715065,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.033,
      "step": 390
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.33955538272857666,
      "learning_rate": 0.00012573329651789297,
      "loss": 0.0338,
      "step": 400
    },
    {
      "epoch": 9.11111111111111,
      "grad_norm": 0.3720948398113251,
      "learning_rate": 0.00012214924986791003,
      "loss": 0.0353,
      "step": 410
    },
    {
      "epoch": 9.333333333333334,
      "grad_norm": 0.2159433513879776,
      "learning_rate": 0.00011853502105738692,
      "loss": 0.0328,
      "step": 420
    },
    {
      "epoch": 9.555555555555555,
      "grad_norm": 0.20489104092121124,
      "learning_rate": 0.00011489553509438657,
      "loss": 0.0351,
      "step": 430
    },
    {
      "epoch": 9.777777777777779,
      "grad_norm": 0.19427303969860077,
      "learning_rate": 0.00011123575140418414,
      "loss": 0.0302,
      "step": 440
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.2984829545021057,
      "learning_rate": 0.00010756065707119729,
      "loss": 0.0285,
      "step": 450
    },
    {
      "epoch": 10.222222222222221,
      "grad_norm": 0.19880931079387665,
      "learning_rate": 0.0001038752600432265,
      "loss": 0.0283,
      "step": 460
    },
    {
      "epoch": 10.444444444444445,
      "grad_norm": 0.30339422821998596,
      "learning_rate": 0.00010018458230726523,
      "loss": 0.0268,
      "step": 470
    },
    {
      "epoch": 10.666666666666666,
      "grad_norm": 0.20127274096012115,
      "learning_rate": 9.649365304617952e-05,
      "loss": 0.031,
      "step": 480
    },
    {
      "epoch": 10.88888888888889,
      "grad_norm": 0.2175353467464447,
      "learning_rate": 9.280750178558138e-05,
      "loss": 0.0259,
      "step": 490
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.26974818110466003,
      "learning_rate": 8.913115154023605e-05,
      "loss": 0.0306,
      "step": 500
    },
    {
      "epoch": 11.333333333333334,
      "grad_norm": 0.4030226767063141,
      "learning_rate": 8.546961196934043e-05,
      "loss": 0.0248,
      "step": 510
    },
    {
      "epoch": 11.555555555555555,
      "grad_norm": 0.23470337688922882,
      "learning_rate": 8.182787255000155e-05,
      "loss": 0.0262,
      "step": 520
    },
    {
      "epoch": 11.777777777777779,
      "grad_norm": 0.40099358558654785,
      "learning_rate": 7.82108957782161e-05,
      "loss": 0.0259,
      "step": 530
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.17941424250602722,
      "learning_rate": 7.462361040661667e-05,
      "loss": 0.0299,
      "step": 540
    },
    {
      "epoch": 12.222222222222221,
      "grad_norm": 0.24401065707206726,
      "learning_rate": 7.107090472819896e-05,
      "loss": 0.0231,
      "step": 550
    },
    {
      "epoch": 12.444444444444445,
      "grad_norm": 0.26819756627082825,
      "learning_rate": 6.755761991518219e-05,
      "loss": 0.0262,
      "step": 560
    },
    {
      "epoch": 12.666666666666666,
      "grad_norm": 0.300659716129303,
      "learning_rate": 6.408854342207982e-05,
      "loss": 0.0289,
      "step": 570
    },
    {
      "epoch": 12.88888888888889,
      "grad_norm": 0.2212854027748108,
      "learning_rate": 6.0668402461969807e-05,
      "loss": 0.0243,
      "step": 580
    },
    {
      "epoch": 13.11111111111111,
      "grad_norm": 0.28721633553504944,
      "learning_rate": 5.730185756485395e-05,
      "loss": 0.0256,
      "step": 590
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 0.2350863218307495,
      "learning_rate": 5.399349622688479e-05,
      "loss": 0.0261,
      "step": 600
    },
    {
      "epoch": 13.555555555555555,
      "grad_norm": 0.31170952320098877,
      "learning_rate": 5.074782665911341e-05,
      "loss": 0.0247,
      "step": 610
    },
    {
      "epoch": 13.777777777777779,
      "grad_norm": 0.18656305968761444,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.0233,
      "step": 620
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.2578571140766144,
      "learning_rate": 4.446216250999641e-05,
      "loss": 0.0257,
      "step": 630
    },
    {
      "epoch": 14.222222222222221,
      "grad_norm": 0.16936838626861572,
      "learning_rate": 4.1430733226599114e-05,
      "loss": 0.0212,
      "step": 640
    },
    {
      "epoch": 14.444444444444445,
      "grad_norm": 0.15445557236671448,
      "learning_rate": 3.8479114637605285e-05,
      "loss": 0.0246,
      "step": 650
    },
    {
      "epoch": 14.666666666666666,
      "grad_norm": 0.1869278848171234,
      "learning_rate": 3.561132883074427e-05,
      "loss": 0.0232,
      "step": 660
    },
    {
      "epoch": 14.88888888888889,
      "grad_norm": 0.20103834569454193,
      "learning_rate": 3.2831283657168275e-05,
      "loss": 0.0226,
      "step": 670
    },
    {
      "epoch": 15.11111111111111,
      "grad_norm": 0.2504471242427826,
      "learning_rate": 3.0142767406333518e-05,
      "loss": 0.0184,
      "step": 680
    },
    {
      "epoch": 15.333333333333334,
      "grad_norm": 0.18746283650398254,
      "learning_rate": 2.7549443643804585e-05,
      "loss": 0.019,
      "step": 690
    },
    {
      "epoch": 15.555555555555555,
      "grad_norm": 0.25808605551719666,
      "learning_rate": 2.505484621901655e-05,
      "loss": 0.0181,
      "step": 700
    },
    {
      "epoch": 15.777777777777779,
      "grad_norm": 0.2831310033798218,
      "learning_rate": 2.2662374449797664e-05,
      "loss": 0.022,
      "step": 710
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.18062320351600647,
      "learning_rate": 2.0375288490214404e-05,
      "loss": 0.0205,
      "step": 720
    },
    {
      "epoch": 16.22222222222222,
      "grad_norm": 0.15133315324783325,
      "learning_rate": 1.819670488805111e-05,
      "loss": 0.0198,
      "step": 730
    },
    {
      "epoch": 16.444444444444443,
      "grad_norm": 0.20342513918876648,
      "learning_rate": 1.6129592337977995e-05,
      "loss": 0.02,
      "step": 740
    },
    {
      "epoch": 16.666666666666668,
      "grad_norm": 0.21008381247520447,
      "learning_rate": 1.4176767636194122e-05,
      "loss": 0.0232,
      "step": 750
    },
    {
      "epoch": 16.88888888888889,
      "grad_norm": 0.25737613439559937,
      "learning_rate": 1.234089184205851e-05,
      "loss": 0.0227,
      "step": 760
    },
    {
      "epoch": 17.11111111111111,
      "grad_norm": 0.15780089795589447,
      "learning_rate": 1.0624466651939247e-05,
      "loss": 0.0203,
      "step": 770
    },
    {
      "epoch": 17.333333333333332,
      "grad_norm": 0.16062302887439728,
      "learning_rate": 9.029830990222132e-06,
      "loss": 0.0244,
      "step": 780
    },
    {
      "epoch": 17.555555555555557,
      "grad_norm": 0.18100588023662567,
      "learning_rate": 7.55915782212413e-06,
      "loss": 0.0173,
      "step": 790
    },
    {
      "epoch": 17.77777777777778,
      "grad_norm": 0.20718730986118317,
      "learning_rate": 6.214451192654747e-06,
      "loss": 0.0186,
      "step": 800
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.18695631623268127,
      "learning_rate": 4.9975434957601264e-06,
      "loss": 0.0177,
      "step": 810
    },
    {
      "epoch": 18.22222222222222,
      "grad_norm": 0.1640794426202774,
      "learning_rate": 3.910092977371394e-06,
      "loss": 0.0169,
      "step": 820
    },
    {
      "epoch": 18.444444444444443,
      "grad_norm": 0.18873189389705658,
      "learning_rate": 2.953581475759404e-06,
      "loss": 0.0214,
      "step": 830
    },
    {
      "epoch": 18.666666666666668,
      "grad_norm": 0.1896572709083557,
      "learning_rate": 2.1293124022754407e-06,
      "loss": 0.0173,
      "step": 840
    },
    {
      "epoch": 18.88888888888889,
      "grad_norm": 0.09888505190610886,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 0.0185,
      "step": 850
    },
    {
      "epoch": 19.11111111111111,
      "grad_norm": 0.17348803579807281,
      "learning_rate": 8.818126393241643e-07,
      "loss": 0.0182,
      "step": 860
    },
    {
      "epoch": 19.333333333333332,
      "grad_norm": 0.20844842493534088,
      "learning_rate": 4.602818827369126e-07,
      "loss": 0.0217,
      "step": 870
    },
    {
      "epoch": 19.555555555555557,
      "grad_norm": 0.16763387620449066,
      "learning_rate": 1.7439110358704602e-07,
      "loss": 0.0175,
      "step": 880
    },
    {
      "epoch": 19.77777777777778,
      "grad_norm": 0.13927114009857178,
      "learning_rate": 2.4529877207557505e-08,
      "loss": 0.0221,
      "step": 890
    },
    {
      "epoch": 19.91111111111111,
      "step": 896,
      "total_flos": 6.431855929189344e+16,
      "train_loss": 0.060006462794262916,
      "train_runtime": 634.4726,
      "train_samples_per_second": 90.381,
      "train_steps_per_second": 1.412
    }
  ],
  "logging_steps": 10,
  "max_steps": 896,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.431855929189344e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}