{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 808,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 1.4873312819674722,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.4428,
      "step": 10
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 0.860149696440848,
      "learning_rate": 2.345679012345679e-06,
      "loss": 0.4068,
      "step": 20
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 0.7730974534228278,
      "learning_rate": 3.580246913580247e-06,
      "loss": 0.3273,
      "step": 30
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 0.5689200686287729,
      "learning_rate": 4.814814814814815e-06,
      "loss": 0.2622,
      "step": 40
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 0.717240303466821,
      "learning_rate": 6.049382716049383e-06,
      "loss": 0.2315,
      "step": 50
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 0.5479796314240546,
      "learning_rate": 7.283950617283952e-06,
      "loss": 0.225,
      "step": 60
    },
    {
      "epoch": 0.17326732673267325,
      "grad_norm": 0.5367981858324066,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.2078,
      "step": 70
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 0.5128703711055814,
      "learning_rate": 9.753086419753087e-06,
      "loss": 0.2007,
      "step": 80
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 0.5500134916740962,
      "learning_rate": 9.997012501794273e-06,
      "loss": 0.2115,
      "step": 90
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 0.5442543564775922,
      "learning_rate": 9.984881908680157e-06,
      "loss": 0.1977,
      "step": 100
    },
    {
      "epoch": 0.2722772277227723,
      "grad_norm": 0.4987905277999744,
      "learning_rate": 9.963444133394478e-06,
      "loss": 0.2044,
      "step": 110
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 0.5792621848377878,
      "learning_rate": 9.93273920201681e-06,
      "loss": 0.1859,
      "step": 120
    },
    {
      "epoch": 0.3217821782178218,
      "grad_norm": 0.4991425649649758,
      "learning_rate": 9.892824443164987e-06,
      "loss": 0.1986,
      "step": 130
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 0.5558327647976072,
      "learning_rate": 9.84377438095789e-06,
      "loss": 0.1972,
      "step": 140
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 0.5522405055451383,
      "learning_rate": 9.785680595872824e-06,
      "loss": 0.1973,
      "step": 150
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.4641525226246223,
      "learning_rate": 9.718651553757266e-06,
      "loss": 0.1848,
      "step": 160
    },
    {
      "epoch": 0.4207920792079208,
      "grad_norm": 0.4712224353128171,
      "learning_rate": 9.642812403314272e-06,
      "loss": 0.1911,
      "step": 170
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 0.5142622413114706,
      "learning_rate": 9.55830474243961e-06,
      "loss": 0.1925,
      "step": 180
    },
    {
      "epoch": 0.47029702970297027,
      "grad_norm": 0.4006105519636306,
      "learning_rate": 9.465286353846905e-06,
      "loss": 0.1866,
      "step": 190
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 0.5073171400534645,
      "learning_rate": 9.36393091047441e-06,
      "loss": 0.185,
      "step": 200
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 0.5880177221650992,
      "learning_rate": 9.254427651223434e-06,
      "loss": 0.1848,
      "step": 210
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 0.4554484357702942,
      "learning_rate": 9.136981027633834e-06,
      "loss": 0.1851,
      "step": 220
    },
    {
      "epoch": 0.5693069306930693,
      "grad_norm": 0.5031293487926348,
      "learning_rate": 9.011810322156269e-06,
      "loss": 0.1948,
      "step": 230
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.4577032226856764,
      "learning_rate": 8.879149238733932e-06,
      "loss": 0.1861,
      "step": 240
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 0.44733995052099396,
      "learning_rate": 8.739245466458187e-06,
      "loss": 0.1757,
      "step": 250
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 0.5406277161031414,
      "learning_rate": 8.592360217112759e-06,
      "loss": 0.1794,
      "step": 260
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 0.4515622758216762,
      "learning_rate": 8.438767737469995e-06,
      "loss": 0.1735,
      "step": 270
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 0.4635294881039678,
      "learning_rate": 8.278754797249702e-06,
      "loss": 0.1713,
      "step": 280
    },
    {
      "epoch": 0.7178217821782178,
      "grad_norm": 0.5013665282058885,
      "learning_rate": 8.11262015369663e-06,
      "loss": 0.1761,
      "step": 290
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.4829501917570715,
      "learning_rate": 7.940673993776258e-06,
      "loss": 0.1874,
      "step": 300
    },
    {
      "epoch": 0.7673267326732673,
      "grad_norm": 0.443719131169877,
      "learning_rate": 7.763237355030384e-06,
      "loss": 0.1683,
      "step": 310
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.4280811144981197,
      "learning_rate": 7.580641526173758e-06,
      "loss": 0.1776,
      "step": 320
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 0.6434688708393701,
      "learning_rate": 7.39322742855097e-06,
      "loss": 0.1861,
      "step": 330
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 0.4538744032232575,
      "learning_rate": 7.201344979608423e-06,
      "loss": 0.1832,
      "step": 340
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 0.4590505681626231,
      "learning_rate": 7.0053524395698345e-06,
      "loss": 0.1778,
      "step": 350
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 0.39529209206101645,
      "learning_rate": 6.805615742535117e-06,
      "loss": 0.1712,
      "step": 360
    },
    {
      "epoch": 0.9158415841584159,
      "grad_norm": 0.5257661202592374,
      "learning_rate": 6.602507813251478e-06,
      "loss": 0.1752,
      "step": 370
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 0.49075057672303185,
      "learning_rate": 6.396407870832419e-06,
      "loss": 0.1691,
      "step": 380
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 0.4063721529471352,
      "learning_rate": 6.187700720724648e-06,
      "loss": 0.1638,
      "step": 390
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 0.49409556281854755,
      "learning_rate": 5.976776036244833e-06,
      "loss": 0.1715,
      "step": 400
    },
    {
      "epoch": 1.0148514851485149,
      "grad_norm": 0.4704764465424178,
      "learning_rate": 5.764027631027659e-06,
      "loss": 0.1338,
      "step": 410
    },
    {
      "epoch": 1.0396039603960396,
      "grad_norm": 0.514030762089054,
      "learning_rate": 5.549852723743564e-06,
      "loss": 0.1068,
      "step": 420
    },
    {
      "epoch": 1.0643564356435644,
      "grad_norm": 0.46024391907618734,
      "learning_rate": 5.334651196459003e-06,
      "loss": 0.1083,
      "step": 430
    },
    {
      "epoch": 1.0891089108910892,
      "grad_norm": 0.5084928690964229,
      "learning_rate": 5.118824848023926e-06,
      "loss": 0.0991,
      "step": 440
    },
    {
      "epoch": 1.113861386138614,
      "grad_norm": 0.5721555377829844,
      "learning_rate": 4.902776643880461e-06,
      "loss": 0.1082,
      "step": 450
    },
    {
      "epoch": 1.1386138613861387,
      "grad_norm": 0.44271050446405025,
      "learning_rate": 4.686909963693498e-06,
      "loss": 0.0998,
      "step": 460
    },
    {
      "epoch": 1.1633663366336633,
      "grad_norm": 0.4765511931794564,
      "learning_rate": 4.47162784820784e-06,
      "loss": 0.1,
      "step": 470
    },
    {
      "epoch": 1.188118811881188,
      "grad_norm": 0.4946911218893508,
      "learning_rate": 4.257332246738201e-06,
      "loss": 0.1019,
      "step": 480
    },
    {
      "epoch": 1.2128712871287128,
      "grad_norm": 0.4965201004334917,
      "learning_rate": 4.04442326669695e-06,
      "loss": 0.1051,
      "step": 490
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 0.5408097804856393,
      "learning_rate": 3.833298426560851e-06,
      "loss": 0.1004,
      "step": 500
    },
    {
      "epoch": 1.2623762376237624,
      "grad_norm": 0.5252320189983105,
      "learning_rate": 3.624351913671571e-06,
      "loss": 0.1014,
      "step": 510
    },
    {
      "epoch": 1.2871287128712872,
      "grad_norm": 0.556206677324514,
      "learning_rate": 3.4179738482556648e-06,
      "loss": 0.1049,
      "step": 520
    },
    {
      "epoch": 1.311881188118812,
      "grad_norm": 0.5360529256375285,
      "learning_rate": 3.214549555038218e-06,
      "loss": 0.1009,
      "step": 530
    },
    {
      "epoch": 1.3366336633663367,
      "grad_norm": 0.48742930116454386,
      "learning_rate": 3.0144588438100693e-06,
      "loss": 0.0999,
      "step": 540
    },
    {
      "epoch": 1.3613861386138613,
      "grad_norm": 0.7874631044020063,
      "learning_rate": 2.8180753002918735e-06,
      "loss": 0.0991,
      "step": 550
    },
    {
      "epoch": 1.386138613861386,
      "grad_norm": 0.4606133875814067,
      "learning_rate": 2.6257655886190147e-06,
      "loss": 0.0933,
      "step": 560
    },
    {
      "epoch": 1.4108910891089108,
      "grad_norm": 0.47731270631998807,
      "learning_rate": 2.4378887667496696e-06,
      "loss": 0.0989,
      "step": 570
    },
    {
      "epoch": 1.4356435643564356,
      "grad_norm": 0.5003301127513975,
      "learning_rate": 2.2547956160742473e-06,
      "loss": 0.0994,
      "step": 580
    },
    {
      "epoch": 1.4603960396039604,
      "grad_norm": 0.5212714732655578,
      "learning_rate": 2.0768279864778475e-06,
      "loss": 0.1083,
      "step": 590
    },
    {
      "epoch": 1.4851485148514851,
      "grad_norm": 0.4573167459369404,
      "learning_rate": 1.9043181580785597e-06,
      "loss": 0.0955,
      "step": 600
    },
    {
      "epoch": 1.50990099009901,
      "grad_norm": 0.5828901902132052,
      "learning_rate": 1.73758822083332e-06,
      "loss": 0.1021,
      "step": 610
    },
    {
      "epoch": 1.5346534653465347,
      "grad_norm": 0.44258879326834666,
      "learning_rate": 1.5769494731696206e-06,
      "loss": 0.0944,
      "step": 620
    },
    {
      "epoch": 1.5594059405940595,
      "grad_norm": 0.5612729118082875,
      "learning_rate": 1.4227018407658822e-06,
      "loss": 0.103,
      "step": 630
    },
    {
      "epoch": 1.5841584158415842,
      "grad_norm": 0.5111939858784064,
      "learning_rate": 1.275133316565691e-06,
      "loss": 0.1015,
      "step": 640
    },
    {
      "epoch": 1.608910891089109,
      "grad_norm": 0.43301100280236354,
      "learning_rate": 1.1345194230714235e-06,
      "loss": 0.0916,
      "step": 650
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.5685808742921838,
      "learning_rate": 1.001122697921197e-06,
      "loss": 0.1006,
      "step": 660
    },
    {
      "epoch": 1.6584158415841586,
      "grad_norm": 0.4732021093665504,
      "learning_rate": 8.751922037096328e-07,
      "loss": 0.0973,
      "step": 670
    },
    {
      "epoch": 1.6831683168316833,
      "grad_norm": 0.5002688727866472,
      "learning_rate": 7.569630629676294e-07,
      "loss": 0.0988,
      "step": 680
    },
    {
      "epoch": 1.7079207920792079,
      "grad_norm": 0.6448602699924979,
      "learning_rate": 6.466560191693566e-07,
      "loss": 0.0948,
      "step": 690
    },
    {
      "epoch": 1.7326732673267327,
      "grad_norm": 0.49223407652600815,
      "learning_rate": 5.444770245861553e-07,
      "loss": 0.0913,
      "step": 700
    },
    {
      "epoch": 1.7574257425742574,
      "grad_norm": 0.4356390296013288,
      "learning_rate": 4.506168557567886e-07,
      "loss": 0.0944,
      "step": 710
    },
    {
      "epoch": 1.7821782178217822,
      "grad_norm": 0.4524339230442861,
      "learning_rate": 3.6525075729205274e-07,
      "loss": 0.0922,
      "step": 720
    },
    {
      "epoch": 1.806930693069307,
      "grad_norm": 0.6615290546421568,
      "learning_rate": 2.8853811467875413e-07,
      "loss": 0.098,
      "step": 730
    },
    {
      "epoch": 1.8316831683168315,
      "grad_norm": 0.49847536579909224,
      "learning_rate": 2.2062215669397201e-07,
      "loss": 0.1025,
      "step": 740
    },
    {
      "epoch": 1.8564356435643563,
      "grad_norm": 0.4027083627268508,
      "learning_rate": 1.616296879852175e-07,
      "loss": 0.0906,
      "step": 750
    },
    {
      "epoch": 1.881188118811881,
      "grad_norm": 0.5545161003969088,
      "learning_rate": 1.1167085231579111e-07,
      "loss": 0.1015,
      "step": 760
    },
    {
      "epoch": 1.9059405940594059,
      "grad_norm": 0.6170175679054791,
      "learning_rate": 7.083892691736428e-08,
      "loss": 0.1024,
      "step": 770
    },
    {
      "epoch": 1.9306930693069306,
      "grad_norm": 0.643468057667551,
      "learning_rate": 3.9210148333763135e-08,
      "loss": 0.0925,
      "step": 780
    },
    {
      "epoch": 1.9554455445544554,
      "grad_norm": 0.4524005775955007,
      "learning_rate": 1.684357008110593e-08,
      "loss": 0.0973,
      "step": 790
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 0.4828849570873087,
      "learning_rate": 3.780952390058379e-09,
      "loss": 0.0901,
      "step": 800
    },
    {
      "epoch": 2.0,
      "step": 808,
      "total_flos": 1.995296975397847e+17,
      "train_loss": 0.15181401895709556,
      "train_runtime": 29257.7471,
      "train_samples_per_second": 0.221,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 10,
  "max_steps": 808,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.995296975397847e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}