{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.820250284414107,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.26715654134750366,
      "learning_rate": 4.9992855064046754e-05,
      "loss": 2.6697,
      "step": 5
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.4067687392234802,
      "learning_rate": 4.997142434019578e-05,
      "loss": 2.5369,
      "step": 10
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.44472697377204895,
      "learning_rate": 4.9935720078139045e-05,
      "loss": 2.5661,
      "step": 15
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.45230674743652344,
      "learning_rate": 4.988576268624979e-05,
      "loss": 2.4824,
      "step": 20
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.4477585554122925,
      "learning_rate": 4.982158071991725e-05,
      "loss": 2.3343,
      "step": 25
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.3630908131599426,
      "learning_rate": 4.974321086522453e-05,
      "loss": 2.4377,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.3237389028072357,
      "learning_rate": 4.9650697917979025e-05,
      "loss": 2.4114,
      "step": 35
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.3014233708381653,
      "learning_rate": 4.954409475810737e-05,
      "loss": 2.2636,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.3054388761520386,
      "learning_rate": 4.942346231942955e-05,
      "loss": 2.2758,
      "step": 45
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.2940792143344879,
      "learning_rate": 4.92888695548294e-05,
      "loss": 2.3207,
      "step": 50
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.25064757466316223,
      "learning_rate": 4.9140393396841565e-05,
      "loss": 2.2209,
      "step": 55
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.3227023780345917,
      "learning_rate": 4.89781187136772e-05,
      "loss": 2.2328,
      "step": 60
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.312673419713974,
      "learning_rate": 4.880213826071375e-05,
      "loss": 2.2737,
      "step": 65
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.26930904388427734,
      "learning_rate": 4.861255262747643e-05,
      "loss": 2.2686,
      "step": 70
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.2343609631061554,
      "learning_rate": 4.8409470180141827e-05,
      "loss": 2.2661,
      "step": 75
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.3088403642177582,
      "learning_rate": 4.8193006999596294e-05,
      "loss": 2.191,
      "step": 80
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.3336387574672699,
      "learning_rate": 4.796328681508473e-05,
      "loss": 2.2106,
      "step": 85
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.28899675607681274,
      "learning_rate": 4.7720440933487575e-05,
      "loss": 2.2347,
      "step": 90
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.30223432183265686,
      "learning_rate": 4.746460816426647e-05,
      "loss": 2.2307,
      "step": 95
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2692021429538727,
      "learning_rate": 4.7195934740121485e-05,
      "loss": 2.1503,
      "step": 100
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3296695053577423,
      "learning_rate": 4.6914574233405236e-05,
      "loss": 2.2145,
      "step": 105
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.28714171051979065,
      "learning_rate": 4.662068746834176e-05,
      "loss": 2.1163,
      "step": 110
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.35001716017723083,
      "learning_rate": 4.6314442429100155e-05,
      "loss": 2.1868,
      "step": 115
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.32721835374832153,
      "learning_rate": 4.599601416377575e-05,
      "loss": 2.1865,
      "step": 120
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.30708980560302734,
      "learning_rate": 4.566558468433344e-05,
      "loss": 2.2035,
      "step": 125
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.3122975528240204,
      "learning_rate": 4.532334286257064e-05,
      "loss": 2.1762,
      "step": 130
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.3531278669834137,
      "learning_rate": 4.496948432215913e-05,
      "loss": 2.2452,
      "step": 135
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3190854489803314,
      "learning_rate": 4.460421132682751e-05,
      "loss": 2.2267,
      "step": 140
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.29605475068092346,
      "learning_rate": 4.4227732664748365e-05,
      "loss": 2.2548,
      "step": 145
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.37863361835479736,
      "learning_rate": 4.384026352919595e-05,
      "loss": 2.2053,
      "step": 150
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.3235403895378113,
      "learning_rate": 4.344202539554285e-05,
      "loss": 2.193,
      "step": 155
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.3326057195663452,
      "learning_rate": 4.3033245894665814e-05,
      "loss": 2.2349,
      "step": 160
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3827252686023712,
      "learning_rate": 4.261415868283304e-05,
      "loss": 2.1247,
      "step": 165
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.34777992963790894,
      "learning_rate": 4.218500330814753e-05,
      "loss": 2.1555,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3294101059436798,
      "learning_rate": 4.174602507362258e-05,
      "loss": 2.1771,
      "step": 175
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.3454132676124573,
      "learning_rate": 4.1297474896967814e-05,
      "loss": 2.1616,
      "step": 180
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.3628969192504883,
      "learning_rate": 4.083960916716597e-05,
      "loss": 2.1681,
      "step": 185
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.31756460666656494,
      "learning_rate": 4.0372689597922215e-05,
      "loss": 2.146,
      "step": 190
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.41087692975997925,
      "learning_rate": 3.989698307806995e-05,
      "loss": 2.2185,
      "step": 195
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.3311336636543274,
      "learning_rate": 3.941276151901853e-05,
      "loss": 2.0976,
      "step": 200
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.38921472430229187,
      "learning_rate": 3.8920301699330076e-05,
      "loss": 2.1204,
      "step": 205
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.31258201599121094,
      "learning_rate": 3.84198851065143e-05,
      "loss": 2.1678,
      "step": 210
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.4159790575504303,
      "learning_rate": 3.791179777613163e-05,
      "loss": 2.2486,
      "step": 215
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3648820221424103,
      "learning_rate": 3.739633012829682e-05,
      "loss": 2.1523,
      "step": 220
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.35387834906578064,
      "learning_rate": 3.6873776801676264e-05,
      "loss": 2.1761,
      "step": 225
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.40865159034729004,
      "learning_rate": 3.6344436485074e-05,
      "loss": 2.219,
      "step": 230
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.40083423256874084,
      "learning_rate": 3.5808611746702814e-05,
      "loss": 2.1755,
      "step": 235
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.3656306564807892,
      "learning_rate": 3.5266608861237724e-05,
      "loss": 2.1917,
      "step": 240
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.3839705288410187,
      "learning_rate": 3.471873763475099e-05,
      "loss": 2.1878,
      "step": 245
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.4037785530090332,
      "learning_rate": 3.4165311227628524e-05,
      "loss": 2.1101,
      "step": 250
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.3458710312843323,
      "learning_rate": 3.3606645975569005e-05,
      "loss": 2.1691,
      "step": 255
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.3371334373950958,
      "learning_rate": 3.304306120876807e-05,
      "loss": 2.1904,
      "step": 260
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.4284100830554962,
      "learning_rate": 3.247487906939076e-05,
      "loss": 2.1688,
      "step": 265
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.3682388365268707,
      "learning_rate": 3.1902424327436734e-05,
      "loss": 2.1691,
      "step": 270
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.32562267780303955,
      "learning_rate": 3.132602419510336e-05,
      "loss": 2.0698,
      "step": 275
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.4634737968444824,
      "learning_rate": 3.0746008139752964e-05,
      "loss": 2.2131,
      "step": 280
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.4514225423336029,
      "learning_rate": 3.0162707695590935e-05,
      "loss": 2.1414,
      "step": 285
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.4424736499786377,
      "learning_rate": 2.9576456274162488e-05,
      "loss": 2.1257,
      "step": 290
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.4680028557777405,
      "learning_rate": 2.8987588973776304e-05,
      "loss": 2.2337,
      "step": 295
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.44635656476020813,
      "learning_rate": 2.8396442387964075e-05,
      "loss": 2.2022,
      "step": 300
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.4005129039287567,
      "learning_rate": 2.7803354413085364e-05,
      "loss": 2.1944,
      "step": 305
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.3982764184474945,
      "learning_rate": 2.72086640551878e-05,
      "loss": 2.0979,
      "step": 310
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.39070507884025574,
      "learning_rate": 2.6612711236232912e-05,
      "loss": 2.1757,
      "step": 315
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.4183822572231293,
      "learning_rate": 2.601583659979851e-05,
      "loss": 2.0571,
      "step": 320
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.39799273014068604,
      "learning_rate": 2.541838131636854e-05,
      "loss": 2.1154,
      "step": 325
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.3967350125312805,
      "learning_rate": 2.4820686888321808e-05,
      "loss": 2.164,
      "step": 330
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.3555432856082916,
      "learning_rate": 2.4223094954730956e-05,
      "loss": 2.1596,
      "step": 335
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.3698050379753113,
      "learning_rate": 2.3625947096083327e-05,
      "loss": 2.0815,
      "step": 340
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.45504623651504517,
      "learning_rate": 2.3029584639035286e-05,
      "loss": 2.0997,
      "step": 345
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.4048606753349304,
      "learning_rate": 2.2434348461311684e-05,
      "loss": 2.1397,
      "step": 350
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.46529653668403625,
      "learning_rate": 2.184057879686185e-05,
      "loss": 2.1781,
      "step": 355
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.4468785226345062,
      "learning_rate": 2.1248615041383685e-05,
      "loss": 2.1155,
      "step": 360
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.49244192242622375,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 2.2141,
      "step": 365
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.45070916414260864,
      "learning_rate": 2.0071457485485463e-05,
      "loss": 2.2219,
      "step": 370
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.392012357711792,
      "learning_rate": 1.94869365422929e-05,
      "loss": 2.1288,
      "step": 375
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.3873184621334076,
      "learning_rate": 1.8905566837925264e-05,
      "loss": 2.1477,
      "step": 380
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.47440674901008606,
      "learning_rate": 1.832768068032678e-05,
      "loss": 2.0753,
      "step": 385
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.5017093420028687,
      "learning_rate": 1.7753608386264196e-05,
      "loss": 2.1999,
      "step": 390
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.3944746255874634,
      "learning_rate": 1.7183678092519385e-05,
      "loss": 2.1569,
      "step": 395
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.4446674883365631,
      "learning_rate": 1.66182155683281e-05,
      "loss": 2.1261,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 657,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.3698387234914304e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}