{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.774593338497289,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015491866769945779,
      "grad_norm": 0.40339195728302,
      "learning_rate": 9.278350515463919e-07,
      "loss": 1.8526,
      "step": 10
    },
    {
      "epoch": 0.030983733539891558,
      "grad_norm": 0.3715074062347412,
      "learning_rate": 1.9587628865979384e-06,
      "loss": 1.8835,
      "step": 20
    },
    {
      "epoch": 0.046475600309837335,
      "grad_norm": 0.3445941209793091,
      "learning_rate": 2.9896907216494846e-06,
      "loss": 1.8733,
      "step": 30
    },
    {
      "epoch": 0.061967467079783116,
      "grad_norm": 0.3444959223270416,
      "learning_rate": 4.020618556701032e-06,
      "loss": 1.8952,
      "step": 40
    },
    {
      "epoch": 0.07745933384972889,
      "grad_norm": 0.3230769634246826,
      "learning_rate": 5.051546391752578e-06,
      "loss": 1.8588,
      "step": 50
    },
    {
      "epoch": 0.09295120061967467,
      "grad_norm": 0.33751699328422546,
      "learning_rate": 6.082474226804124e-06,
      "loss": 1.8307,
      "step": 60
    },
    {
      "epoch": 0.10844306738962045,
      "grad_norm": 0.2963869869709015,
      "learning_rate": 7.113402061855671e-06,
      "loss": 1.8419,
      "step": 70
    },
    {
      "epoch": 0.12393493415956623,
      "grad_norm": 0.2550879716873169,
      "learning_rate": 8.144329896907216e-06,
      "loss": 1.8281,
      "step": 80
    },
    {
      "epoch": 0.139426800929512,
      "grad_norm": 0.22610870003700256,
      "learning_rate": 9.175257731958764e-06,
      "loss": 1.8005,
      "step": 90
    },
    {
      "epoch": 0.15491866769945778,
      "grad_norm": 0.1930716335773468,
      "learning_rate": 1.0206185567010309e-05,
      "loss": 1.7897,
      "step": 100
    },
    {
      "epoch": 0.17041053446940357,
      "grad_norm": 0.18139410018920898,
      "learning_rate": 1.1237113402061856e-05,
      "loss": 1.7181,
      "step": 110
    },
    {
      "epoch": 0.18590240123934934,
      "grad_norm": 0.1586223542690277,
      "learning_rate": 1.2268041237113405e-05,
      "loss": 1.7328,
      "step": 120
    },
    {
      "epoch": 0.2013942680092951,
      "grad_norm": 0.2047862708568573,
      "learning_rate": 1.3298969072164948e-05,
      "loss": 1.7268,
      "step": 130
    },
    {
      "epoch": 0.2168861347792409,
      "grad_norm": 0.16858699917793274,
      "learning_rate": 1.4329896907216495e-05,
      "loss": 1.7029,
      "step": 140
    },
    {
      "epoch": 0.23237800154918667,
      "grad_norm": 0.15446807444095612,
      "learning_rate": 1.5360824742268042e-05,
      "loss": 1.7114,
      "step": 150
    },
    {
      "epoch": 0.24786986831913246,
      "grad_norm": 0.1550971418619156,
      "learning_rate": 1.6391752577319588e-05,
      "loss": 1.7054,
      "step": 160
    },
    {
      "epoch": 0.26336173508907823,
      "grad_norm": 0.13774091005325317,
      "learning_rate": 1.7422680412371137e-05,
      "loss": 1.685,
      "step": 170
    },
    {
      "epoch": 0.278853601859024,
      "grad_norm": 0.13972033560276031,
      "learning_rate": 1.8453608247422682e-05,
      "loss": 1.6774,
      "step": 180
    },
    {
      "epoch": 0.29434546862896976,
      "grad_norm": 0.14723576605319977,
      "learning_rate": 1.9484536082474227e-05,
      "loss": 1.63,
      "step": 190
    },
    {
      "epoch": 0.30983733539891556,
      "grad_norm": 0.1486756056547165,
      "learning_rate": 1.9999592986072886e-05,
      "loss": 1.6429,
      "step": 200
    },
    {
      "epoch": 0.32532920216886135,
      "grad_norm": 0.1460903435945511,
      "learning_rate": 1.9996337073445673e-05,
      "loss": 1.669,
      "step": 210
    },
    {
      "epoch": 0.34082106893880715,
      "grad_norm": 0.16247884929180145,
      "learning_rate": 1.9989826308331103e-05,
      "loss": 1.6572,
      "step": 220
    },
    {
      "epoch": 0.3563129357087529,
      "grad_norm": 0.16369281709194183,
      "learning_rate": 1.998006281066369e-05,
      "loss": 1.6545,
      "step": 230
    },
    {
      "epoch": 0.3718048024786987,
      "grad_norm": 0.1450214833021164,
      "learning_rate": 1.996704975948236e-05,
      "loss": 1.6762,
      "step": 240
    },
    {
      "epoch": 0.3872966692486445,
      "grad_norm": 0.17881567776203156,
      "learning_rate": 1.9950791391895335e-05,
      "loss": 1.6397,
      "step": 250
    },
    {
      "epoch": 0.4027885360185902,
      "grad_norm": 0.15863952040672302,
      "learning_rate": 1.9931293001700518e-05,
      "loss": 1.6597,
      "step": 260
    },
    {
      "epoch": 0.418280402788536,
      "grad_norm": 0.1730642467737198,
      "learning_rate": 1.990856093766179e-05,
      "loss": 1.6586,
      "step": 270
    },
    {
      "epoch": 0.4337722695584818,
      "grad_norm": 0.14790953695774078,
      "learning_rate": 1.988260260144185e-05,
      "loss": 1.6416,
      "step": 280
    },
    {
      "epoch": 0.4492641363284276,
      "grad_norm": 0.14577385783195496,
      "learning_rate": 1.9853426445192175e-05,
      "loss": 1.659,
      "step": 290
    },
    {
      "epoch": 0.46475600309837334,
      "grad_norm": 0.13978034257888794,
      "learning_rate": 1.9821041968800982e-05,
      "loss": 1.6362,
      "step": 300
    },
    {
      "epoch": 0.48024786986831913,
      "grad_norm": 0.17719446122646332,
      "learning_rate": 1.9785459716800005e-05,
      "loss": 1.6648,
      "step": 310
    },
    {
      "epoch": 0.4957397366382649,
      "grad_norm": 0.1415952891111374,
      "learning_rate": 1.9746691274931168e-05,
      "loss": 1.6518,
      "step": 320
    },
    {
      "epoch": 0.5112316034082107,
      "grad_norm": 0.1455707997083664,
      "learning_rate": 1.970474926637418e-05,
      "loss": 1.6445,
      "step": 330
    },
    {
      "epoch": 0.5267234701781565,
      "grad_norm": 0.19560855627059937,
      "learning_rate": 1.9659647347636422e-05,
      "loss": 1.6557,
      "step": 340
    },
    {
      "epoch": 0.5422153369481022,
      "grad_norm": 0.15447896718978882,
      "learning_rate": 1.961140020410627e-05,
      "loss": 1.6361,
      "step": 350
    },
    {
      "epoch": 0.557707203718048,
      "grad_norm": 0.17043063044548035,
      "learning_rate": 1.9560023545271512e-05,
      "loss": 1.6289,
      "step": 360
    },
    {
      "epoch": 0.5731990704879938,
      "grad_norm": 0.16939246654510498,
      "learning_rate": 1.9505534099604245e-05,
      "loss": 1.6318,
      "step": 370
    },
    {
      "epoch": 0.5886909372579395,
      "grad_norm": 0.1785915642976761,
      "learning_rate": 1.9447949609114018e-05,
      "loss": 1.6321,
      "step": 380
    },
    {
      "epoch": 0.6041828040278854,
      "grad_norm": 0.16734299063682556,
      "learning_rate": 1.938728882357093e-05,
      "loss": 1.6443,
      "step": 390
    },
    {
      "epoch": 0.6196746707978311,
      "grad_norm": 0.18670211732387543,
      "learning_rate": 1.932357149440067e-05,
      "loss": 1.6683,
      "step": 400
    },
    {
      "epoch": 0.635166537567777,
      "grad_norm": 0.15596874058246613,
      "learning_rate": 1.925681836825331e-05,
      "loss": 1.6336,
      "step": 410
    },
    {
      "epoch": 0.6506584043377227,
      "grad_norm": 0.18547730147838593,
      "learning_rate": 1.9187051180248134e-05,
      "loss": 1.6374,
      "step": 420
    },
    {
      "epoch": 0.6661502711076684,
      "grad_norm": 0.15439730882644653,
      "learning_rate": 1.9114292646896574e-05,
      "loss": 1.6298,
      "step": 430
    },
    {
      "epoch": 0.6816421378776143,
      "grad_norm": 0.15702180564403534,
      "learning_rate": 1.9038566458705615e-05,
      "loss": 1.6235,
      "step": 440
    },
    {
      "epoch": 0.69713400464756,
      "grad_norm": 0.20213943719863892,
      "learning_rate": 1.895989727246405e-05,
      "loss": 1.6511,
      "step": 450
    },
    {
      "epoch": 0.7126258714175058,
      "grad_norm": 0.17505770921707153,
      "learning_rate": 1.8878310703214148e-05,
      "loss": 1.6385,
      "step": 460
    },
    {
      "epoch": 0.7281177381874516,
      "grad_norm": 0.29876482486724854,
      "learning_rate": 1.879383331591123e-05,
      "loss": 1.6508,
      "step": 470
    },
    {
      "epoch": 0.7436096049573974,
      "grad_norm": 0.16168834269046783,
      "learning_rate": 1.8706492616774043e-05,
      "loss": 1.6424,
      "step": 480
    },
    {
      "epoch": 0.7591014717273431,
      "grad_norm": 0.1786322444677353,
      "learning_rate": 1.86163170443286e-05,
      "loss": 1.6699,
      "step": 490
    },
    {
      "epoch": 0.774593338497289,
      "grad_norm": 0.16993215680122375,
      "learning_rate": 1.8523335960148446e-05,
      "loss": 1.6499,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.572020564311736e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}