{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 478,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020920502092050207,
      "grad_norm": 8.136081343052572,
      "learning_rate": 1.0416666666666666e-08,
      "loss": 1.2533,
      "step": 1
    },
    {
      "epoch": 0.010460251046025104,
      "grad_norm": 10.869224095264249,
      "learning_rate": 5.208333333333333e-08,
      "loss": 1.3074,
      "step": 5
    },
    {
      "epoch": 0.02092050209205021,
      "grad_norm": 9.394947250234965,
      "learning_rate": 1.0416666666666667e-07,
      "loss": 1.3511,
      "step": 10
    },
    {
      "epoch": 0.03138075313807531,
      "grad_norm": 8.48453952211364,
      "learning_rate": 1.5624999999999999e-07,
      "loss": 1.3286,
      "step": 15
    },
    {
      "epoch": 0.04184100418410042,
      "grad_norm": 9.807884523848902,
      "learning_rate": 2.0833333333333333e-07,
      "loss": 1.2539,
      "step": 20
    },
    {
      "epoch": 0.05230125523012552,
      "grad_norm": 6.770187197984029,
      "learning_rate": 2.604166666666667e-07,
      "loss": 1.2428,
      "step": 25
    },
    {
      "epoch": 0.06276150627615062,
      "grad_norm": 4.388418711512584,
      "learning_rate": 3.1249999999999997e-07,
      "loss": 1.2573,
      "step": 30
    },
    {
      "epoch": 0.07322175732217573,
      "grad_norm": 3.7767106766677507,
      "learning_rate": 3.645833333333333e-07,
      "loss": 1.254,
      "step": 35
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 3.8857851665569503,
      "learning_rate": 4.1666666666666667e-07,
      "loss": 1.193,
      "step": 40
    },
    {
      "epoch": 0.09414225941422594,
      "grad_norm": 3.6981444602921743,
      "learning_rate": 4.6874999999999996e-07,
      "loss": 1.2297,
      "step": 45
    },
    {
      "epoch": 0.10460251046025104,
      "grad_norm": 3.164525008947102,
      "learning_rate": 4.999733114418725e-07,
      "loss": 1.2045,
      "step": 50
    },
    {
      "epoch": 0.11506276150627615,
      "grad_norm": 3.3438200347539975,
      "learning_rate": 4.996731305997416e-07,
      "loss": 1.2055,
      "step": 55
    },
    {
      "epoch": 0.12552301255230125,
      "grad_norm": 3.4475160228942117,
      "learning_rate": 4.990398100856366e-07,
      "loss": 1.1582,
      "step": 60
    },
    {
      "epoch": 0.13598326359832635,
      "grad_norm": 4.990341002466793,
      "learning_rate": 4.980741949411839e-07,
      "loss": 1.169,
      "step": 65
    },
    {
      "epoch": 0.14644351464435146,
      "grad_norm": 3.0806862112851725,
      "learning_rate": 4.967775735898179e-07,
      "loss": 1.1512,
      "step": 70
    },
    {
      "epoch": 0.15690376569037656,
      "grad_norm": 3.2012998938874717,
      "learning_rate": 4.951516761176343e-07,
      "loss": 1.1196,
      "step": 75
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 3.254309758852426,
      "learning_rate": 4.931986719649298e-07,
      "loss": 1.1321,
      "step": 80
    },
    {
      "epoch": 0.17782426778242677,
      "grad_norm": 3.521038876761785,
      "learning_rate": 4.909211670315114e-07,
      "loss": 1.176,
      "step": 85
    },
    {
      "epoch": 0.18828451882845187,
      "grad_norm": 3.1094901411244407,
      "learning_rate": 4.883222001996351e-07,
      "loss": 1.0846,
      "step": 90
    },
    {
      "epoch": 0.19874476987447698,
      "grad_norm": 3.944726072257309,
      "learning_rate": 4.854052392792161e-07,
      "loss": 1.1643,
      "step": 95
    },
    {
      "epoch": 0.20920502092050208,
      "grad_norm": 3.0199061104695275,
      "learning_rate": 4.821741763807186e-07,
      "loss": 1.1587,
      "step": 100
    },
    {
      "epoch": 0.2196652719665272,
      "grad_norm": 3.0664109423340156,
      "learning_rate": 4.786333227218995e-07,
      "loss": 1.1017,
      "step": 105
    },
    {
      "epoch": 0.2301255230125523,
      "grad_norm": 3.5363910368317404,
      "learning_rate": 4.747874028753375e-07,
      "loss": 1.118,
      "step": 110
    },
    {
      "epoch": 0.2405857740585774,
      "grad_norm": 3.2790793251193913,
      "learning_rate": 4.706415484644195e-07,
      "loss": 1.1024,
      "step": 115
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 3.1085664448119616,
      "learning_rate": 4.662012913161997e-07,
      "loss": 1.1253,
      "step": 120
    },
    {
      "epoch": 0.2615062761506276,
      "grad_norm": 3.17942285679677,
      "learning_rate": 4.614725560802639e-07,
      "loss": 1.1144,
      "step": 125
    },
    {
      "epoch": 0.2719665271966527,
      "grad_norm": 2.9359440437528233,
      "learning_rate": 4.5646165232345103e-07,
      "loss": 1.0742,
      "step": 130
    },
    {
      "epoch": 0.2824267782426778,
      "grad_norm": 3.378239775065935,
      "learning_rate": 4.511752661109768e-07,
      "loss": 1.1246,
      "step": 135
    },
    {
      "epoch": 0.2928870292887029,
      "grad_norm": 3.0222815305213646,
      "learning_rate": 4.456204510851956e-07,
      "loss": 1.0949,
      "step": 140
    },
    {
      "epoch": 0.303347280334728,
      "grad_norm": 3.305312909236648,
      "learning_rate": 4.398046190539024e-07,
      "loss": 1.1114,
      "step": 145
    },
    {
      "epoch": 0.3138075313807531,
      "grad_norm": 3.31590711665521,
      "learning_rate": 4.337355301007335e-07,
      "loss": 1.1266,
      "step": 150
    },
    {
      "epoch": 0.32426778242677823,
      "grad_norm": 3.7988390548789135,
      "learning_rate": 4.2742128223086115e-07,
      "loss": 1.0817,
      "step": 155
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 3.5053528166093195,
      "learning_rate": 4.2087030056579986e-07,
      "loss": 1.1247,
      "step": 160
    },
    {
      "epoch": 0.34518828451882844,
      "grad_norm": 3.002251062725114,
      "learning_rate": 4.140913261017382e-07,
      "loss": 1.0626,
      "step": 165
    },
    {
      "epoch": 0.35564853556485354,
      "grad_norm": 3.5448336222698997,
      "learning_rate": 4.070934040463998e-07,
      "loss": 1.0787,
      "step": 170
    },
    {
      "epoch": 0.36610878661087864,
      "grad_norm": 2.917615696290126,
      "learning_rate": 3.9988587174999306e-07,
      "loss": 1.0624,
      "step": 175
    },
    {
      "epoch": 0.37656903765690375,
      "grad_norm": 3.333598035642462,
      "learning_rate": 3.9247834624635404e-07,
      "loss": 1.0995,
      "step": 180
    },
    {
      "epoch": 0.38702928870292885,
      "grad_norm": 3.128496425971326,
      "learning_rate": 3.848807114209074e-07,
      "loss": 1.0672,
      "step": 185
    },
    {
      "epoch": 0.39748953974895396,
      "grad_norm": 3.178190677786049,
      "learning_rate": 3.7710310482256523e-07,
      "loss": 1.086,
      "step": 190
    },
    {
      "epoch": 0.40794979079497906,
      "grad_norm": 3.5211557677293204,
      "learning_rate": 3.691559041371631e-07,
      "loss": 1.0735,
      "step": 195
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 5.250340368942305,
      "learning_rate": 3.610497133404795e-07,
      "loss": 1.084,
      "step": 200
    },
    {
      "epoch": 0.42887029288702927,
      "grad_norm": 3.0435886010974325,
      "learning_rate": 3.5279534854931674e-07,
      "loss": 1.0937,
      "step": 205
    },
    {
      "epoch": 0.4393305439330544,
      "grad_norm": 3.155631541031488,
      "learning_rate": 3.4440382358952115e-07,
      "loss": 1.0526,
      "step": 210
    },
    {
      "epoch": 0.4497907949790795,
      "grad_norm": 3.1856253958176373,
      "learning_rate": 3.3588633530019866e-07,
      "loss": 1.0744,
      "step": 215
    },
    {
      "epoch": 0.4602510460251046,
      "grad_norm": 3.2478748519097516,
      "learning_rate": 3.272542485937368e-07,
      "loss": 1.0996,
      "step": 220
    },
    {
      "epoch": 0.4707112970711297,
      "grad_norm": 3.5150799679920652,
      "learning_rate": 3.185190812915646e-07,
      "loss": 1.0786,
      "step": 225
    },
    {
      "epoch": 0.4811715481171548,
      "grad_norm": 3.2027896128694904,
      "learning_rate": 3.096924887558854e-07,
      "loss": 1.0722,
      "step": 230
    },
    {
      "epoch": 0.4916317991631799,
      "grad_norm": 3.0097866657045333,
      "learning_rate": 3.007862483378906e-07,
      "loss": 1.0753,
      "step": 235
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 2.8959084947264464,
      "learning_rate": 2.9181224366319943e-07,
      "loss": 1.0898,
      "step": 240
    },
    {
      "epoch": 0.5125523012552301,
      "grad_norm": 3.1849250279587555,
      "learning_rate": 2.827824487755007e-07,
      "loss": 1.1032,
      "step": 245
    },
    {
      "epoch": 0.5230125523012552,
      "grad_norm": 3.151630569719264,
      "learning_rate": 2.7370891215954565e-07,
      "loss": 1.0704,
      "step": 250
    },
    {
      "epoch": 0.5334728033472803,
      "grad_norm": 3.2021502155528534,
      "learning_rate": 2.646037406648165e-07,
      "loss": 1.0897,
      "step": 255
    },
    {
      "epoch": 0.5439330543933054,
      "grad_norm": 3.281246167153216,
      "learning_rate": 2.55479083351317e-07,
      "loss": 1.0572,
      "step": 260
    },
    {
      "epoch": 0.5543933054393305,
      "grad_norm": 3.286796060289107,
      "learning_rate": 2.463471152790427e-07,
      "loss": 1.0995,
      "step": 265
    },
    {
      "epoch": 0.5648535564853556,
      "grad_norm": 3.161375590564493,
      "learning_rate": 2.3722002126275822e-07,
      "loss": 1.1033,
      "step": 270
    },
    {
      "epoch": 0.5753138075313807,
      "grad_norm": 3.2395710239773834,
      "learning_rate": 2.2810997961375938e-07,
      "loss": 1.0621,
      "step": 275
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 3.246465238459929,
      "learning_rate": 2.19029145890313e-07,
      "loss": 1.0814,
      "step": 280
    },
    {
      "epoch": 0.5962343096234309,
      "grad_norm": 3.2179889434846087,
      "learning_rate": 2.0998963667845536e-07,
      "loss": 1.0905,
      "step": 285
    },
    {
      "epoch": 0.606694560669456,
      "grad_norm": 3.1419612482251154,
      "learning_rate": 2.0100351342479216e-07,
      "loss": 1.0668,
      "step": 290
    },
    {
      "epoch": 0.6171548117154811,
      "grad_norm": 3.5676672142270487,
      "learning_rate": 1.920827663428714e-07,
      "loss": 1.056,
      "step": 295
    },
    {
      "epoch": 0.6276150627615062,
      "grad_norm": 3.1612890211744267,
      "learning_rate": 1.8323929841460178e-07,
      "loss": 1.095,
      "step": 300
    },
    {
      "epoch": 0.6380753138075314,
      "grad_norm": 3.2825957498988956,
      "learning_rate": 1.7448490950806548e-07,
      "loss": 1.0861,
      "step": 305
    },
    {
      "epoch": 0.6485355648535565,
      "grad_norm": 3.726600439972812,
      "learning_rate": 1.6583128063291573e-07,
      "loss": 1.0501,
      "step": 310
    },
    {
      "epoch": 0.6589958158995816,
      "grad_norm": 3.1847430333577544,
      "learning_rate": 1.572899583543671e-07,
      "loss": 1.0644,
      "step": 315
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 3.229050818238049,
      "learning_rate": 1.488723393865766e-07,
      "loss": 1.0764,
      "step": 320
    },
    {
      "epoch": 0.6799163179916318,
      "grad_norm": 3.0713199002348155,
      "learning_rate": 1.4058965538597032e-07,
      "loss": 1.0416,
      "step": 325
    },
    {
      "epoch": 0.6903765690376569,
      "grad_norm": 3.357568728209587,
      "learning_rate": 1.3245295796480788e-07,
      "loss": 1.0694,
      "step": 330
    },
    {
      "epoch": 0.700836820083682,
      "grad_norm": 3.2375362653987705,
      "learning_rate": 1.2447310394498017e-07,
      "loss": 1.0341,
      "step": 335
    },
    {
      "epoch": 0.7112970711297071,
      "grad_norm": 3.2586888391876148,
      "learning_rate": 1.1666074087171627e-07,
      "loss": 1.0602,
      "step": 340
    },
    {
      "epoch": 0.7217573221757322,
      "grad_norm": 3.3346267359627126,
      "learning_rate": 1.090262928065293e-07,
      "loss": 1.0648,
      "step": 345
    },
    {
      "epoch": 0.7322175732217573,
      "grad_norm": 2.8836656878180857,
      "learning_rate": 1.0157994641835734e-07,
      "loss": 1.0398,
      "step": 350
    },
    {
      "epoch": 0.7426778242677824,
      "grad_norm": 3.206673738900126,
      "learning_rate": 9.433163739145771e-08,
      "loss": 1.0688,
      "step": 355
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 3.2095084267239495,
      "learning_rate": 8.729103716819111e-08,
      "loss": 1.0279,
      "step": 360
    },
    {
      "epoch": 0.7635983263598326,
      "grad_norm": 3.20440166136788,
      "learning_rate": 8.046754004438428e-08,
      "loss": 1.059,
      "step": 365
    },
    {
      "epoch": 0.7740585774058577,
      "grad_norm": 3.742393968055389,
      "learning_rate": 7.387025063449081e-08,
      "loss": 1.0595,
      "step": 370
    },
    {
      "epoch": 0.7845188284518828,
      "grad_norm": 3.2395714997445193,
      "learning_rate": 6.75079717232744e-08,
      "loss": 1.0486,
      "step": 375
    },
    {
      "epoch": 0.7949790794979079,
      "grad_norm": 3.2720407044526403,
      "learning_rate": 6.138919252022435e-08,
      "loss": 1.0704,
      "step": 380
    },
    {
      "epoch": 0.805439330543933,
      "grad_norm": 3.370063395554973,
      "learning_rate": 5.552207733237543e-08,
      "loss": 1.0606,
      "step": 385
    },
    {
      "epoch": 0.8158995815899581,
      "grad_norm": 3.0968930333404625,
      "learning_rate": 4.991445467064689e-08,
      "loss": 1.0566,
      "step": 390
    },
    {
      "epoch": 0.8263598326359832,
      "grad_norm": 3.3774763830658534,
      "learning_rate": 4.4573806804234335e-08,
      "loss": 1.0499,
      "step": 395
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 3.44447850480557,
      "learning_rate": 3.9507259776993954e-08,
      "loss": 1.0559,
      "step": 400
    },
    {
      "epoch": 0.8472803347280334,
      "grad_norm": 3.1498166707617594,
      "learning_rate": 3.472157389913874e-08,
      "loss": 1.0547,
      "step": 405
    },
    {
      "epoch": 0.8577405857740585,
      "grad_norm": 3.3701661155234865,
      "learning_rate": 3.022313472693447e-08,
      "loss": 1.0985,
      "step": 410
    },
    {
      "epoch": 0.8682008368200836,
      "grad_norm": 3.3374460611814154,
      "learning_rate": 2.601794454243139e-08,
      "loss": 1.0592,
      "step": 415
    },
    {
      "epoch": 0.8786610878661087,
      "grad_norm": 3.390815082624942,
      "learning_rate": 2.2111614344599684e-08,
      "loss": 1.0762,
      "step": 420
    },
    {
      "epoch": 0.8891213389121339,
      "grad_norm": 3.189149656101972,
      "learning_rate": 1.850935636255496e-08,
      "loss": 1.0932,
      "step": 425
    },
    {
      "epoch": 0.899581589958159,
      "grad_norm": 3.9882552930751176,
      "learning_rate": 1.521597710086439e-08,
      "loss": 1.0775,
      "step": 430
    },
    {
      "epoch": 0.9100418410041841,
      "grad_norm": 3.4652282672677934,
      "learning_rate": 1.2235870926211616e-08,
      "loss": 1.0556,
      "step": 435
    },
    {
      "epoch": 0.9205020920502092,
      "grad_norm": 4.369109278161751,
      "learning_rate": 9.57301420397924e-09,
      "loss": 1.0415,
      "step": 440
    },
    {
      "epoch": 0.9309623430962343,
      "grad_norm": 3.2834964218858356,
      "learning_rate": 7.230959992571367e-09,
      "loss": 1.0751,
      "step": 445
    },
    {
      "epoch": 0.9414225941422594,
      "grad_norm": 3.300455182998976,
      "learning_rate": 5.212833302556258e-09,
      "loss": 1.0353,
      "step": 450
    },
    {
      "epoch": 0.9518828451882845,
      "grad_norm": 3.201301345623655,
      "learning_rate": 3.521326926954532e-09,
      "loss": 1.0647,
      "step": 455
    },
    {
      "epoch": 0.9623430962343096,
      "grad_norm": 3.3648524524406622,
      "learning_rate": 2.158697848236607e-09,
      "loss": 1.0874,
      "step": 460
    },
    {
      "epoch": 0.9728033472803347,
      "grad_norm": 3.743838451577809,
      "learning_rate": 1.126764226823812e-09,
      "loss": 1.0479,
      "step": 465
    },
    {
      "epoch": 0.9832635983263598,
      "grad_norm": 3.2562966396262167,
      "learning_rate": 4.269029751107489e-10,
      "loss": 1.0317,
      "step": 470
    },
    {
      "epoch": 0.9937238493723849,
      "grad_norm": 3.1980061195336846,
      "learning_rate": 6.004792024680294e-11,
      "loss": 1.0685,
      "step": 475
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0374830961227417,
      "eval_runtime": 10.4617,
      "eval_samples_per_second": 191.174,
      "eval_steps_per_second": 3.059,
      "step": 478
    },
    {
      "epoch": 1.0,
      "step": 478,
      "total_flos": 97516887736320.0,
      "train_loss": 1.1027952946379593,
      "train_runtime": 1452.993,
      "train_samples_per_second": 42.075,
      "train_steps_per_second": 0.329
    }
  ],
  "logging_steps": 5,
  "max_steps": 478,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 97516887736320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}