{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1158,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034549773267112935,
      "grad_norm": 2.8664734447528373,
      "learning_rate": 5.428571428571429e-06,
      "loss": 1.1657718658447265,
      "step": 20
    },
    {
      "epoch": 0.06909954653422587,
      "grad_norm": 1.4337217467356131,
      "learning_rate": 9.999686962985852e-06,
      "loss": 0.6347041606903077,
      "step": 40
    },
    {
      "epoch": 0.1036493198013388,
      "grad_norm": 1.5646783257715595,
      "learning_rate": 9.98873478261223e-06,
      "loss": 0.5277756690979004,
      "step": 60
    },
    {
      "epoch": 0.13819909306845174,
      "grad_norm": 1.3776757150298382,
      "learning_rate": 9.962169926344231e-06,
      "loss": 0.4968242168426514,
      "step": 80
    },
    {
      "epoch": 0.17274886633556466,
      "grad_norm": 1.456320044091266,
      "learning_rate": 9.920075531191371e-06,
      "loss": 0.47785301208496095,
      "step": 100
    },
    {
      "epoch": 0.2072986396026776,
      "grad_norm": 1.4629934882500373,
      "learning_rate": 9.862583335194882e-06,
      "loss": 0.46541714668273926,
      "step": 120
    },
    {
      "epoch": 0.24184841286979053,
      "grad_norm": 1.2573863753540042,
      "learning_rate": 9.78987326514215e-06,
      "loss": 0.4540743827819824,
      "step": 140
    },
    {
      "epoch": 0.2763981861369035,
      "grad_norm": 1.4552134997800634,
      "learning_rate": 9.702172873470304e-06,
      "loss": 0.4439044952392578,
      "step": 160
    },
    {
      "epoch": 0.3109479594040164,
      "grad_norm": 1.292855098237038,
      "learning_rate": 9.599756626121244e-06,
      "loss": 0.44383878707885743,
      "step": 180
    },
    {
      "epoch": 0.3454977326711293,
      "grad_norm": 1.2762551801880975,
      "learning_rate": 9.482945043576787e-06,
      "loss": 0.4401799201965332,
      "step": 200
    },
    {
      "epoch": 0.38004750593824227,
      "grad_norm": 1.3204027527217352,
      "learning_rate": 9.352103697762169e-06,
      "loss": 0.43046369552612307,
      "step": 220
    },
    {
      "epoch": 0.4145972792053552,
      "grad_norm": 1.3410304541508509,
      "learning_rate": 9.207642067957168e-06,
      "loss": 0.4260669708251953,
      "step": 240
    },
    {
      "epoch": 0.44914705247246817,
      "grad_norm": 1.2568026750759995,
      "learning_rate": 9.050012259295368e-06,
      "loss": 0.4213873863220215,
      "step": 260
    },
    {
      "epoch": 0.48369682573958106,
      "grad_norm": 1.2507870469399514,
      "learning_rate": 8.879707587862148e-06,
      "loss": 0.41970076560974123,
      "step": 280
    },
    {
      "epoch": 0.518246599006694,
      "grad_norm": 1.2488543877405978,
      "learning_rate": 8.697261036819417e-06,
      "loss": 0.41837573051452637,
      "step": 300
    },
    {
      "epoch": 0.552796372273807,
      "grad_norm": 1.2844449753227947,
      "learning_rate": 8.503243588388843e-06,
      "loss": 0.4127053260803223,
      "step": 320
    },
    {
      "epoch": 0.5873461455409199,
      "grad_norm": 1.197504948600083,
      "learning_rate": 8.298262436913722e-06,
      "loss": 0.4118648052215576,
      "step": 340
    },
    {
      "epoch": 0.6218959188080329,
      "grad_norm": 1.4393022629841532,
      "learning_rate": 8.082959088591896e-06,
      "loss": 0.4030599594116211,
      "step": 360
    },
    {
      "epoch": 0.6564456920751458,
      "grad_norm": 1.2673985088219022,
      "learning_rate": 7.858007353826759e-06,
      "loss": 0.40169849395751955,
      "step": 380
    },
    {
      "epoch": 0.6909954653422586,
      "grad_norm": 1.2559499407176486,
      "learning_rate": 7.624111238479486e-06,
      "loss": 0.40119156837463377,
      "step": 400
    },
    {
      "epoch": 0.7255452386093716,
      "grad_norm": 1.1626677281742914,
      "learning_rate": 7.382002740621927e-06,
      "loss": 0.4003328323364258,
      "step": 420
    },
    {
      "epoch": 0.7600950118764845,
      "grad_norm": 1.182922120217234,
      "learning_rate": 7.13243955968551e-06,
      "loss": 0.3960381031036377,
      "step": 440
    },
    {
      "epoch": 0.7946447851435975,
      "grad_norm": 1.1782145409948144,
      "learning_rate": 6.876202725175495e-06,
      "loss": 0.395128870010376,
      "step": 460
    },
    {
      "epoch": 0.8291945584107104,
      "grad_norm": 1.2169213876196088,
      "learning_rate": 6.6140941523717525e-06,
      "loss": 0.3930006980895996,
      "step": 480
    },
    {
      "epoch": 0.8637443316778234,
      "grad_norm": 1.170249594242604,
      "learning_rate": 6.346934132665716e-06,
      "loss": 0.3871454238891602,
      "step": 500
    },
    {
      "epoch": 0.8637443316778234,
      "eval_loss": 0.3875163495540619,
      "eval_runtime": 37.7513,
      "eval_samples_per_second": 19.84,
      "eval_steps_per_second": 2.49,
      "step": 500
    },
    {
      "epoch": 0.8982941049449363,
      "grad_norm": 1.0955834666492503,
      "learning_rate": 6.075558766387704e-06,
      "loss": 0.38927350044250486,
      "step": 520
    },
    {
      "epoch": 0.9328438782120493,
      "grad_norm": 1.3090310964244551,
      "learning_rate": 5.800817346158799e-06,
      "loss": 0.388520622253418,
      "step": 540
    },
    {
      "epoch": 0.9673936514791621,
      "grad_norm": 1.2864568791701871,
      "learning_rate": 5.523569698956324e-06,
      "loss": 0.3871021747589111,
      "step": 560
    },
    {
      "epoch": 1.0017274886633556,
      "grad_norm": 1.2455996447929154,
      "learning_rate": 5.244683495211132e-06,
      "loss": 0.3767592430114746,
      "step": 580
    },
    {
      "epoch": 1.0362772619304685,
      "grad_norm": 1.194543172520135,
      "learning_rate": 4.965031533358145e-06,
      "loss": 0.30886454582214357,
      "step": 600
    },
    {
      "epoch": 1.0708270351975815,
      "grad_norm": 1.1992991389773715,
      "learning_rate": 4.68548900833834e-06,
      "loss": 0.3078233957290649,
      "step": 620
    },
    {
      "epoch": 1.1053768084646944,
      "grad_norm": 1.125091424298445,
      "learning_rate": 4.406930772600691e-06,
      "loss": 0.30689167976379395,
      "step": 640
    },
    {
      "epoch": 1.1399265817318074,
      "grad_norm": 1.2403216264401389,
      "learning_rate": 4.130228598175936e-06,
      "loss": 0.30630016326904297,
      "step": 660
    },
    {
      "epoch": 1.1744763549989203,
      "grad_norm": 1.1381163816712636,
      "learning_rate": 3.8562484483908185e-06,
      "loss": 0.30424864292144777,
      "step": 680
    },
    {
      "epoch": 1.2090261282660333,
      "grad_norm": 1.1742097580246738,
      "learning_rate": 3.585847767761129e-06,
      "loss": 0.3021160840988159,
      "step": 700
    },
    {
      "epoch": 1.2435759015331462,
      "grad_norm": 1.2248624691829175,
      "learning_rate": 3.319872798545123e-06,
      "loss": 0.30002799034118655,
      "step": 720
    },
    {
      "epoch": 1.2781256748002592,
      "grad_norm": 1.2148897545015434,
      "learning_rate": 3.0591559323553745e-06,
      "loss": 0.301845121383667,
      "step": 740
    },
    {
      "epoch": 1.3126754480673721,
      "grad_norm": 1.112604129255114,
      "learning_rate": 2.8045131051173996e-06,
      "loss": 0.3007266283035278,
      "step": 760
    },
    {
      "epoch": 1.3472252213344849,
      "grad_norm": 1.148763078129724,
      "learning_rate": 2.5567412435277937e-06,
      "loss": 0.30183887481689453,
      "step": 780
    },
    {
      "epoch": 1.381774994601598,
      "grad_norm": 1.1300915836806016,
      "learning_rate": 2.3166157710033806e-06,
      "loss": 0.3000323295593262,
      "step": 800
    },
    {
      "epoch": 1.4163247678687108,
      "grad_norm": 1.1280332290813746,
      "learning_rate": 2.0848881809267185e-06,
      "loss": 0.29852092266082764,
      "step": 820
    },
    {
      "epoch": 1.450874541135824,
      "grad_norm": 1.0682281947302132,
      "learning_rate": 1.8622836847827508e-06,
      "loss": 0.29711189270019533,
      "step": 840
    },
    {
      "epoch": 1.4854243144029367,
      "grad_norm": 1.1453197277270952,
      "learning_rate": 1.6494989425468737e-06,
      "loss": 0.297352933883667,
      "step": 860
    },
    {
      "epoch": 1.5199740876700498,
      "grad_norm": 1.1787570897480169,
      "learning_rate": 1.4471998824274553e-06,
      "loss": 0.29497063159942627,
      "step": 880
    },
    {
      "epoch": 1.5545238609371625,
      "grad_norm": 1.3230431638895255,
      "learning_rate": 1.256019616786045e-06,
      "loss": 0.2936807632446289,
      "step": 900
    },
    {
      "epoch": 1.5890736342042755,
      "grad_norm": 1.069651807110778,
      "learning_rate": 1.0765564607576295e-06,
      "loss": 0.2928804874420166,
      "step": 920
    },
    {
      "epoch": 1.6236234074713884,
      "grad_norm": 1.111691766766449,
      "learning_rate": 9.093720597717909e-07,
      "loss": 0.2927506446838379,
      "step": 940
    },
    {
      "epoch": 1.6581731807385014,
      "grad_norm": 1.0773830043790051,
      "learning_rate": 7.549896318348826e-07,
      "loss": 0.29113221168518066,
      "step": 960
    },
    {
      "epoch": 1.6927229540056143,
      "grad_norm": 1.0898618499808255,
      "learning_rate": 6.138923300741412e-07,
      "loss": 0.29058592319488524,
      "step": 980
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 1.0384255493399033,
      "learning_rate": 4.865217306682874e-07,
      "loss": 0.2897153854370117,
      "step": 1000
    },
    {
      "epoch": 1.7272727272727273,
      "eval_loss": 0.36538058519363403,
      "eval_runtime": 37.9727,
      "eval_samples_per_second": 19.725,
      "eval_steps_per_second": 2.475,
      "step": 1000
    },
    {
      "epoch": 1.7618225005398402,
      "grad_norm": 1.0643360983205403,
      "learning_rate": 3.732764508967829e-07,
      "loss": 0.28726768493652344,
      "step": 1020
    },
    {
      "epoch": 1.7963722738069532,
      "grad_norm": 1.0855983344721238,
      "learning_rate": 2.7451090163266026e-07,
      "loss": 0.2893477439880371,
      "step": 1040
    },
    {
      "epoch": 1.8309220470740661,
      "grad_norm": 0.9933868135273795,
      "learning_rate": 1.905341781831238e-07,
      "loss": 0.28991625308990476,
      "step": 1060
    },
    {
      "epoch": 1.8654718203411789,
      "grad_norm": 1.0692513926799851,
      "learning_rate": 1.216090929491176e-07,
      "loss": 0.28725690841674806,
      "step": 1080
    },
    {
      "epoch": 1.900021593608292,
      "grad_norm": 1.0625508095647955,
      "learning_rate": 6.795135293124311e-08,
      "loss": 0.28940911293029786,
      "step": 1100
    },
    {
      "epoch": 1.9345713668754048,
      "grad_norm": 1.0321730234385396,
      "learning_rate": 2.9728884656088918e-08,
      "loss": 0.28683788776397706,
      "step": 1120
    },
    {
      "epoch": 1.969121140142518,
      "grad_norm": 1.048313636296385,
      "learning_rate": 7.061308635684105e-09,
      "loss": 0.2892473220825195,
      "step": 1140
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.364047110080719,
      "eval_runtime": 38.3588,
      "eval_samples_per_second": 19.526,
      "eval_steps_per_second": 2.451,
      "step": 1158
    }
  ],
  "logging_steps": 20,
  "max_steps": 1158,
  "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": 850997071052800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}