{
  "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": 38.749080099489724,
      "learning_rate": 1.111111111111111e-06,
      "loss": 3.2158,
      "step": 10
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 39.64900559019991,
      "learning_rate": 2.345679012345679e-06,
      "loss": 2.4344,
      "step": 20
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 2.416463732570817,
      "learning_rate": 3.580246913580247e-06,
      "loss": 1.1085,
      "step": 30
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 4.162559676174374,
      "learning_rate": 4.814814814814815e-06,
      "loss": 1.0109,
      "step": 40
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 1.4037017225614896,
      "learning_rate": 6.049382716049383e-06,
      "loss": 0.4737,
      "step": 50
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 1.6166445320035476,
      "learning_rate": 7.283950617283952e-06,
      "loss": 0.4355,
      "step": 60
    },
    {
      "epoch": 0.17326732673267325,
      "grad_norm": 1.141640311828574,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.3468,
      "step": 70
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 1.197800510887127,
      "learning_rate": 9.753086419753087e-06,
      "loss": 0.2905,
      "step": 80
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 1.0980962734091972,
      "learning_rate": 9.997012501794273e-06,
      "loss": 0.2852,
      "step": 90
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 0.8706925934126661,
      "learning_rate": 9.984881908680157e-06,
      "loss": 0.2626,
      "step": 100
    },
    {
      "epoch": 0.2722772277227723,
      "grad_norm": 0.9744111977727423,
      "learning_rate": 9.963444133394478e-06,
      "loss": 0.2696,
      "step": 110
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 2.203688809185736,
      "learning_rate": 9.93273920201681e-06,
      "loss": 0.254,
      "step": 120
    },
    {
      "epoch": 0.3217821782178218,
      "grad_norm": 0.6909534190939396,
      "learning_rate": 9.892824443164987e-06,
      "loss": 0.2412,
      "step": 130
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 0.9726066930137242,
      "learning_rate": 9.84377438095789e-06,
      "loss": 0.2374,
      "step": 140
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 0.9033174763116004,
      "learning_rate": 9.785680595872824e-06,
      "loss": 0.2236,
      "step": 150
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.9978308920092659,
      "learning_rate": 9.718651553757266e-06,
      "loss": 0.2294,
      "step": 160
    },
    {
      "epoch": 0.4207920792079208,
      "grad_norm": 4.058405361629531,
      "learning_rate": 9.642812403314272e-06,
      "loss": 0.2266,
      "step": 170
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 1.3629688635899981,
      "learning_rate": 9.55830474243961e-06,
      "loss": 0.2266,
      "step": 180
    },
    {
      "epoch": 0.47029702970297027,
      "grad_norm": 1.2375201071505648,
      "learning_rate": 9.465286353846905e-06,
      "loss": 0.2192,
      "step": 190
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 0.7234385452967922,
      "learning_rate": 9.36393091047441e-06,
      "loss": 0.2212,
      "step": 200
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 0.7326619260019385,
      "learning_rate": 9.254427651223434e-06,
      "loss": 0.2194,
      "step": 210
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 1.160310177931889,
      "learning_rate": 9.136981027633834e-06,
      "loss": 0.2207,
      "step": 220
    },
    {
      "epoch": 0.5693069306930693,
      "grad_norm": 0.8422477849196854,
      "learning_rate": 9.011810322156269e-06,
      "loss": 0.217,
      "step": 230
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 1.5735296786321598,
      "learning_rate": 8.879149238733932e-06,
      "loss": 0.2142,
      "step": 240
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 1.05917908340436,
      "learning_rate": 8.739245466458187e-06,
      "loss": 0.2009,
      "step": 250
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 0.8374503267424538,
      "learning_rate": 8.592360217112759e-06,
      "loss": 0.2276,
      "step": 260
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 3.9597090992745034,
      "learning_rate": 8.438767737469995e-06,
      "loss": 0.2122,
      "step": 270
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 0.7976525324791283,
      "learning_rate": 8.278754797249702e-06,
      "loss": 0.2032,
      "step": 280
    },
    {
      "epoch": 0.7178217821782178,
      "grad_norm": 0.7744706010278902,
      "learning_rate": 8.11262015369663e-06,
      "loss": 0.2195,
      "step": 290
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.8161719072903669,
      "learning_rate": 7.940673993776258e-06,
      "loss": 0.21,
      "step": 300
    },
    {
      "epoch": 0.7673267326732673,
      "grad_norm": 1.0715150167394496,
      "learning_rate": 7.763237355030384e-06,
      "loss": 0.2142,
      "step": 310
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 2.803631363059706,
      "learning_rate": 7.580641526173758e-06,
      "loss": 0.2167,
      "step": 320
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 1.6402074825817914,
      "learning_rate": 7.39322742855097e-06,
      "loss": 0.1964,
      "step": 330
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 2.7431663603349308,
      "learning_rate": 7.201344979608423e-06,
      "loss": 0.2146,
      "step": 340
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 0.6620649226382208,
      "learning_rate": 7.0053524395698345e-06,
      "loss": 0.2037,
      "step": 350
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 1.0418484850219463,
      "learning_rate": 6.805615742535117e-06,
      "loss": 0.2063,
      "step": 360
    },
    {
      "epoch": 0.9158415841584159,
      "grad_norm": 1.0624343454733385,
      "learning_rate": 6.602507813251478e-06,
      "loss": 0.2133,
      "step": 370
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 0.8571908786810298,
      "learning_rate": 6.396407870832419e-06,
      "loss": 0.1935,
      "step": 380
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 1.1625392933521244,
      "learning_rate": 6.187700720724648e-06,
      "loss": 0.19,
      "step": 390
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 0.7676371278259425,
      "learning_rate": 5.976776036244833e-06,
      "loss": 0.1969,
      "step": 400
    },
    {
      "epoch": 1.0148514851485149,
      "grad_norm": 0.5723958610359834,
      "learning_rate": 5.764027631027659e-06,
      "loss": 0.16,
      "step": 410
    },
    {
      "epoch": 1.0396039603960396,
      "grad_norm": 0.6439856648791892,
      "learning_rate": 5.549852723743564e-06,
      "loss": 0.1317,
      "step": 420
    },
    {
      "epoch": 1.0643564356435644,
      "grad_norm": 0.8430846385011965,
      "learning_rate": 5.334651196459003e-06,
      "loss": 0.1326,
      "step": 430
    },
    {
      "epoch": 1.0891089108910892,
      "grad_norm": 0.7075121256426331,
      "learning_rate": 5.118824848023926e-06,
      "loss": 0.1282,
      "step": 440
    },
    {
      "epoch": 1.113861386138614,
      "grad_norm": 0.7098250623843386,
      "learning_rate": 4.902776643880461e-06,
      "loss": 0.1298,
      "step": 450
    },
    {
      "epoch": 1.1386138613861387,
      "grad_norm": 0.5746472756447318,
      "learning_rate": 4.686909963693498e-06,
      "loss": 0.1324,
      "step": 460
    },
    {
      "epoch": 1.1633663366336633,
      "grad_norm": 0.752011250724735,
      "learning_rate": 4.47162784820784e-06,
      "loss": 0.1318,
      "step": 470
    },
    {
      "epoch": 1.188118811881188,
      "grad_norm": 0.7690625261604315,
      "learning_rate": 4.257332246738201e-06,
      "loss": 0.1267,
      "step": 480
    },
    {
      "epoch": 1.2128712871287128,
      "grad_norm": 0.7370929567026177,
      "learning_rate": 4.04442326669695e-06,
      "loss": 0.1286,
      "step": 490
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 2.60432798001788,
      "learning_rate": 3.833298426560851e-06,
      "loss": 0.135,
      "step": 500
    },
    {
      "epoch": 1.2623762376237624,
      "grad_norm": 0.5943041120513542,
      "learning_rate": 3.624351913671571e-06,
      "loss": 0.1219,
      "step": 510
    },
    {
      "epoch": 1.2871287128712872,
      "grad_norm": 0.838743852289041,
      "learning_rate": 3.4179738482556648e-06,
      "loss": 0.1401,
      "step": 520
    },
    {
      "epoch": 1.311881188118812,
      "grad_norm": 0.9067824903652668,
      "learning_rate": 3.214549555038218e-06,
      "loss": 0.1311,
      "step": 530
    },
    {
      "epoch": 1.3366336633663367,
      "grad_norm": 0.6227118274844176,
      "learning_rate": 3.0144588438100693e-06,
      "loss": 0.1254,
      "step": 540
    },
    {
      "epoch": 1.3613861386138613,
      "grad_norm": 0.7977679577819297,
      "learning_rate": 2.8180753002918735e-06,
      "loss": 0.1332,
      "step": 550
    },
    {
      "epoch": 1.386138613861386,
      "grad_norm": 0.6196310809476595,
      "learning_rate": 2.6257655886190147e-06,
      "loss": 0.1211,
      "step": 560
    },
    {
      "epoch": 1.4108910891089108,
      "grad_norm": 0.6084298472807999,
      "learning_rate": 2.4378887667496696e-06,
      "loss": 0.1368,
      "step": 570
    },
    {
      "epoch": 1.4356435643564356,
      "grad_norm": 1.4399382283539155,
      "learning_rate": 2.2547956160742473e-06,
      "loss": 0.1267,
      "step": 580
    },
    {
      "epoch": 1.4603960396039604,
      "grad_norm": 0.7985993051553937,
      "learning_rate": 2.0768279864778475e-06,
      "loss": 0.1206,
      "step": 590
    },
    {
      "epoch": 1.4851485148514851,
      "grad_norm": 0.7931208510059602,
      "learning_rate": 1.9043181580785597e-06,
      "loss": 0.1383,
      "step": 600
    },
    {
      "epoch": 1.50990099009901,
      "grad_norm": 0.512755394763236,
      "learning_rate": 1.73758822083332e-06,
      "loss": 0.1122,
      "step": 610
    },
    {
      "epoch": 1.5346534653465347,
      "grad_norm": 0.6491078299788842,
      "learning_rate": 1.5769494731696206e-06,
      "loss": 0.1296,
      "step": 620
    },
    {
      "epoch": 1.5594059405940595,
      "grad_norm": 0.7130269697667891,
      "learning_rate": 1.4227018407658822e-06,
      "loss": 0.1264,
      "step": 630
    },
    {
      "epoch": 1.5841584158415842,
      "grad_norm": 0.5915982928372153,
      "learning_rate": 1.275133316565691e-06,
      "loss": 0.1229,
      "step": 640
    },
    {
      "epoch": 1.608910891089109,
      "grad_norm": 2.214393925964167,
      "learning_rate": 1.1345194230714235e-06,
      "loss": 0.1248,
      "step": 650
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.7240627506654617,
      "learning_rate": 1.001122697921197e-06,
      "loss": 0.1141,
      "step": 660
    },
    {
      "epoch": 1.6584158415841586,
      "grad_norm": 0.5350731786159315,
      "learning_rate": 8.751922037096328e-07,
      "loss": 0.131,
      "step": 670
    },
    {
      "epoch": 1.6831683168316833,
      "grad_norm": 0.7015404378394352,
      "learning_rate": 7.569630629676294e-07,
      "loss": 0.1229,
      "step": 680
    },
    {
      "epoch": 1.7079207920792079,
      "grad_norm": 0.5929124037254383,
      "learning_rate": 6.466560191693566e-07,
      "loss": 0.1208,
      "step": 690
    },
    {
      "epoch": 1.7326732673267327,
      "grad_norm": 0.7861365186727924,
      "learning_rate": 5.444770245861553e-07,
      "loss": 0.1305,
      "step": 700
    },
    {
      "epoch": 1.7574257425742574,
      "grad_norm": 0.6518766942066165,
      "learning_rate": 4.506168557567886e-07,
      "loss": 0.1161,
      "step": 710
    },
    {
      "epoch": 1.7821782178217822,
      "grad_norm": 0.683101648152514,
      "learning_rate": 3.6525075729205274e-07,
      "loss": 0.1221,
      "step": 720
    },
    {
      "epoch": 1.806930693069307,
      "grad_norm": 0.6879134500414074,
      "learning_rate": 2.8853811467875413e-07,
      "loss": 0.1203,
      "step": 730
    },
    {
      "epoch": 1.8316831683168315,
      "grad_norm": 1.8254784501234913,
      "learning_rate": 2.2062215669397201e-07,
      "loss": 0.1191,
      "step": 740
    },
    {
      "epoch": 1.8564356435643563,
      "grad_norm": 1.0911513255316725,
      "learning_rate": 1.616296879852175e-07,
      "loss": 0.1279,
      "step": 750
    },
    {
      "epoch": 1.881188118811881,
      "grad_norm": 0.7511673072617823,
      "learning_rate": 1.1167085231579111e-07,
      "loss": 0.1146,
      "step": 760
    },
    {
      "epoch": 1.9059405940594059,
      "grad_norm": 0.6796776730908214,
      "learning_rate": 7.083892691736428e-08,
      "loss": 0.1196,
      "step": 770
    },
    {
      "epoch": 1.9306930693069306,
      "grad_norm": 0.6872639303078989,
      "learning_rate": 3.9210148333763135e-08,
      "loss": 0.1217,
      "step": 780
    },
    {
      "epoch": 1.9554455445544554,
      "grad_norm": 0.582235081912157,
      "learning_rate": 1.684357008110593e-08,
      "loss": 0.1153,
      "step": 790
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 0.7623957535259693,
      "learning_rate": 3.780952390058379e-09,
      "loss": 0.1268,
      "step": 800
    },
    {
      "epoch": 2.0,
      "step": 808,
      "total_flos": 606591045337088.0,
      "train_loss": 0.26673450984872216,
      "train_runtime": 25532.5977,
      "train_samples_per_second": 0.253,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 10,
  "max_steps": 808,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 606591045337088.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}