{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2504472271914132,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 0.5825825929641724,
      "learning_rate": 0.00019928443649373882,
      "loss": 1.248,
      "num_input_tokens_seen": 6646,
      "step": 10
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.5380188822746277,
      "learning_rate": 0.00019856887298747765,
      "loss": 0.5478,
      "num_input_tokens_seen": 13063,
      "step": 20
    },
    {
      "epoch": 0.01073345259391771,
      "grad_norm": 0.3872911036014557,
      "learning_rate": 0.00019785330948121648,
      "loss": 0.5135,
      "num_input_tokens_seen": 19512,
      "step": 30
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.4991438686847687,
      "learning_rate": 0.0001971377459749553,
      "loss": 0.5092,
      "num_input_tokens_seen": 26884,
      "step": 40
    },
    {
      "epoch": 0.017889087656529516,
      "grad_norm": 0.6744784116744995,
      "learning_rate": 0.0001964221824686941,
      "loss": 0.4799,
      "num_input_tokens_seen": 34831,
      "step": 50
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 0.5413841009140015,
      "learning_rate": 0.00019570661896243293,
      "loss": 0.4738,
      "num_input_tokens_seen": 40074,
      "step": 60
    },
    {
      "epoch": 0.025044722719141325,
      "grad_norm": 0.33517029881477356,
      "learning_rate": 0.00019499105545617174,
      "loss": 0.4907,
      "num_input_tokens_seen": 47194,
      "step": 70
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 0.34275758266448975,
      "learning_rate": 0.00019427549194991057,
      "loss": 0.4642,
      "num_input_tokens_seen": 53439,
      "step": 80
    },
    {
      "epoch": 0.03220035778175313,
      "grad_norm": 0.4074145257472992,
      "learning_rate": 0.00019355992844364938,
      "loss": 0.4431,
      "num_input_tokens_seen": 59366,
      "step": 90
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 0.372760534286499,
      "learning_rate": 0.0001928443649373882,
      "loss": 0.4824,
      "num_input_tokens_seen": 66414,
      "step": 100
    },
    {
      "epoch": 0.03935599284436494,
      "grad_norm": 0.35169002413749695,
      "learning_rate": 0.00019212880143112702,
      "loss": 0.4863,
      "num_input_tokens_seen": 73451,
      "step": 110
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 0.4088020324707031,
      "learning_rate": 0.00019141323792486585,
      "loss": 0.4792,
      "num_input_tokens_seen": 81934,
      "step": 120
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.40062326192855835,
      "learning_rate": 0.00019069767441860466,
      "loss": 0.4607,
      "num_input_tokens_seen": 88335,
      "step": 130
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 0.5044320225715637,
      "learning_rate": 0.0001899821109123435,
      "loss": 0.456,
      "num_input_tokens_seen": 96192,
      "step": 140
    },
    {
      "epoch": 0.05366726296958855,
      "grad_norm": 0.4566495418548584,
      "learning_rate": 0.0001892665474060823,
      "loss": 0.429,
      "num_input_tokens_seen": 101609,
      "step": 150
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 0.4657338559627533,
      "learning_rate": 0.0001885509838998211,
      "loss": 0.4445,
      "num_input_tokens_seen": 107467,
      "step": 160
    },
    {
      "epoch": 0.06082289803220036,
      "grad_norm": 0.5721924304962158,
      "learning_rate": 0.00018783542039355994,
      "loss": 0.4304,
      "num_input_tokens_seen": 113612,
      "step": 170
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 0.2883516848087311,
      "learning_rate": 0.00018711985688729877,
      "loss": 0.4525,
      "num_input_tokens_seen": 121416,
      "step": 180
    },
    {
      "epoch": 0.06797853309481217,
      "grad_norm": 0.5061659216880798,
      "learning_rate": 0.00018640429338103758,
      "loss": 0.4439,
      "num_input_tokens_seen": 128284,
      "step": 190
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 0.3323754072189331,
      "learning_rate": 0.00018568872987477638,
      "loss": 0.4489,
      "num_input_tokens_seen": 135571,
      "step": 200
    },
    {
      "epoch": 0.07513416815742398,
      "grad_norm": 0.5354058742523193,
      "learning_rate": 0.00018497316636851522,
      "loss": 0.4634,
      "num_input_tokens_seen": 141479,
      "step": 210
    },
    {
      "epoch": 0.07871198568872988,
      "grad_norm": 0.4328760504722595,
      "learning_rate": 0.00018425760286225405,
      "loss": 0.4545,
      "num_input_tokens_seen": 147677,
      "step": 220
    },
    {
      "epoch": 0.08228980322003578,
      "grad_norm": 0.28675127029418945,
      "learning_rate": 0.00018354203935599286,
      "loss": 0.4814,
      "num_input_tokens_seen": 154847,
      "step": 230
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 0.31572216749191284,
      "learning_rate": 0.00018282647584973166,
      "loss": 0.446,
      "num_input_tokens_seen": 162267,
      "step": 240
    },
    {
      "epoch": 0.08944543828264759,
      "grad_norm": 0.360166996717453,
      "learning_rate": 0.0001821109123434705,
      "loss": 0.4549,
      "num_input_tokens_seen": 168817,
      "step": 250
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.342385470867157,
      "learning_rate": 0.0001813953488372093,
      "loss": 0.4297,
      "num_input_tokens_seen": 174828,
      "step": 260
    },
    {
      "epoch": 0.09660107334525939,
      "grad_norm": 0.37481924891471863,
      "learning_rate": 0.00018067978533094814,
      "loss": 0.4314,
      "num_input_tokens_seen": 181578,
      "step": 270
    },
    {
      "epoch": 0.1001788908765653,
      "grad_norm": 0.28545519709587097,
      "learning_rate": 0.00017996422182468694,
      "loss": 0.4332,
      "num_input_tokens_seen": 187842,
      "step": 280
    },
    {
      "epoch": 0.1037567084078712,
      "grad_norm": 0.38877248764038086,
      "learning_rate": 0.00017924865831842578,
      "loss": 0.4248,
      "num_input_tokens_seen": 194651,
      "step": 290
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 0.30087631940841675,
      "learning_rate": 0.00017853309481216458,
      "loss": 0.4405,
      "num_input_tokens_seen": 202203,
      "step": 300
    },
    {
      "epoch": 0.11091234347048301,
      "grad_norm": 0.33470776677131653,
      "learning_rate": 0.00017781753130590342,
      "loss": 0.4485,
      "num_input_tokens_seen": 210364,
      "step": 310
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 0.44205668568611145,
      "learning_rate": 0.00017710196779964222,
      "loss": 0.4431,
      "num_input_tokens_seen": 217965,
      "step": 320
    },
    {
      "epoch": 0.11806797853309481,
      "grad_norm": 0.39270082116127014,
      "learning_rate": 0.00017638640429338106,
      "loss": 0.4475,
      "num_input_tokens_seen": 224249,
      "step": 330
    },
    {
      "epoch": 0.12164579606440072,
      "grad_norm": 0.37138304114341736,
      "learning_rate": 0.00017567084078711986,
      "loss": 0.4139,
      "num_input_tokens_seen": 230513,
      "step": 340
    },
    {
      "epoch": 0.1252236135957066,
      "grad_norm": 0.32019296288490295,
      "learning_rate": 0.00017495527728085867,
      "loss": 0.4488,
      "num_input_tokens_seen": 237103,
      "step": 350
    },
    {
      "epoch": 0.12880143112701253,
      "grad_norm": 0.42748796939849854,
      "learning_rate": 0.0001742397137745975,
      "loss": 0.4059,
      "num_input_tokens_seen": 242530,
      "step": 360
    },
    {
      "epoch": 0.13237924865831843,
      "grad_norm": 0.39997342228889465,
      "learning_rate": 0.00017352415026833634,
      "loss": 0.4069,
      "num_input_tokens_seen": 247524,
      "step": 370
    },
    {
      "epoch": 0.13595706618962433,
      "grad_norm": 0.45402902364730835,
      "learning_rate": 0.00017280858676207514,
      "loss": 0.4354,
      "num_input_tokens_seen": 252526,
      "step": 380
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.500701904296875,
      "learning_rate": 0.00017209302325581395,
      "loss": 0.4421,
      "num_input_tokens_seen": 258974,
      "step": 390
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 0.2604714035987854,
      "learning_rate": 0.00017137745974955278,
      "loss": 0.4338,
      "num_input_tokens_seen": 265411,
      "step": 400
    },
    {
      "epoch": 0.14669051878354203,
      "grad_norm": 0.5467566251754761,
      "learning_rate": 0.00017066189624329162,
      "loss": 0.4336,
      "num_input_tokens_seen": 271069,
      "step": 410
    },
    {
      "epoch": 0.15026833631484796,
      "grad_norm": 0.4278429448604584,
      "learning_rate": 0.00016994633273703042,
      "loss": 0.4384,
      "num_input_tokens_seen": 277913,
      "step": 420
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.38349634408950806,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.445,
      "num_input_tokens_seen": 285726,
      "step": 430
    },
    {
      "epoch": 0.15742397137745975,
      "grad_norm": 0.298753559589386,
      "learning_rate": 0.00016851520572450806,
      "loss": 0.411,
      "num_input_tokens_seen": 293886,
      "step": 440
    },
    {
      "epoch": 0.16100178890876565,
      "grad_norm": 0.4590730667114258,
      "learning_rate": 0.00016779964221824687,
      "loss": 0.4441,
      "num_input_tokens_seen": 300933,
      "step": 450
    },
    {
      "epoch": 0.16457960644007155,
      "grad_norm": 0.25614652037620544,
      "learning_rate": 0.0001670840787119857,
      "loss": 0.4201,
      "num_input_tokens_seen": 306782,
      "step": 460
    },
    {
      "epoch": 0.16815742397137745,
      "grad_norm": 0.3007524013519287,
      "learning_rate": 0.0001663685152057245,
      "loss": 0.444,
      "num_input_tokens_seen": 314243,
      "step": 470
    },
    {
      "epoch": 0.17173524150268335,
      "grad_norm": 0.4292968809604645,
      "learning_rate": 0.00016565295169946334,
      "loss": 0.4089,
      "num_input_tokens_seen": 319432,
      "step": 480
    },
    {
      "epoch": 0.17531305903398928,
      "grad_norm": 0.31139102578163147,
      "learning_rate": 0.00016493738819320215,
      "loss": 0.4244,
      "num_input_tokens_seen": 325211,
      "step": 490
    },
    {
      "epoch": 0.17889087656529518,
      "grad_norm": 0.34276363253593445,
      "learning_rate": 0.00016422182468694098,
      "loss": 0.4133,
      "num_input_tokens_seen": 332100,
      "step": 500
    },
    {
      "epoch": 0.18246869409660108,
      "grad_norm": 0.39435234665870667,
      "learning_rate": 0.0001635062611806798,
      "loss": 0.4428,
      "num_input_tokens_seen": 337848,
      "step": 510
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.2763209640979767,
      "learning_rate": 0.00016279069767441862,
      "loss": 0.4464,
      "num_input_tokens_seen": 345759,
      "step": 520
    },
    {
      "epoch": 0.18962432915921287,
      "grad_norm": 0.2753828763961792,
      "learning_rate": 0.00016207513416815743,
      "loss": 0.438,
      "num_input_tokens_seen": 354078,
      "step": 530
    },
    {
      "epoch": 0.19320214669051877,
      "grad_norm": 0.3228139579296112,
      "learning_rate": 0.00016135957066189623,
      "loss": 0.4314,
      "num_input_tokens_seen": 360961,
      "step": 540
    },
    {
      "epoch": 0.1967799642218247,
      "grad_norm": 0.30050089955329895,
      "learning_rate": 0.00016064400715563507,
      "loss": 0.4364,
      "num_input_tokens_seen": 367083,
      "step": 550
    },
    {
      "epoch": 0.2003577817531306,
      "grad_norm": 0.3418981432914734,
      "learning_rate": 0.0001599284436493739,
      "loss": 0.4329,
      "num_input_tokens_seen": 373196,
      "step": 560
    },
    {
      "epoch": 0.2039355992844365,
      "grad_norm": 0.36333030462265015,
      "learning_rate": 0.0001592128801431127,
      "loss": 0.4482,
      "num_input_tokens_seen": 380449,
      "step": 570
    },
    {
      "epoch": 0.2075134168157424,
      "grad_norm": 0.2979726195335388,
      "learning_rate": 0.00015849731663685151,
      "loss": 0.4258,
      "num_input_tokens_seen": 386577,
      "step": 580
    },
    {
      "epoch": 0.2110912343470483,
      "grad_norm": 0.2969113886356354,
      "learning_rate": 0.00015778175313059035,
      "loss": 0.433,
      "num_input_tokens_seen": 392953,
      "step": 590
    },
    {
      "epoch": 0.2146690518783542,
      "grad_norm": 0.4132014811038971,
      "learning_rate": 0.00015706618962432918,
      "loss": 0.4148,
      "num_input_tokens_seen": 399368,
      "step": 600
    },
    {
      "epoch": 0.2182468694096601,
      "grad_norm": 0.35863760113716125,
      "learning_rate": 0.000156350626118068,
      "loss": 0.4105,
      "num_input_tokens_seen": 407343,
      "step": 610
    },
    {
      "epoch": 0.22182468694096602,
      "grad_norm": 0.287056028842926,
      "learning_rate": 0.0001556350626118068,
      "loss": 0.4495,
      "num_input_tokens_seen": 413867,
      "step": 620
    },
    {
      "epoch": 0.22540250447227192,
      "grad_norm": 0.41710999608039856,
      "learning_rate": 0.00015491949910554563,
      "loss": 0.426,
      "num_input_tokens_seen": 422712,
      "step": 630
    },
    {
      "epoch": 0.22898032200357782,
      "grad_norm": 0.42847341299057007,
      "learning_rate": 0.00015420393559928446,
      "loss": 0.4163,
      "num_input_tokens_seen": 428523,
      "step": 640
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.35523882508277893,
      "learning_rate": 0.00015348837209302327,
      "loss": 0.4237,
      "num_input_tokens_seen": 436283,
      "step": 650
    },
    {
      "epoch": 0.23613595706618962,
      "grad_norm": 0.32238948345184326,
      "learning_rate": 0.00015277280858676207,
      "loss": 0.4527,
      "num_input_tokens_seen": 444368,
      "step": 660
    },
    {
      "epoch": 0.23971377459749552,
      "grad_norm": 0.3075689375400543,
      "learning_rate": 0.0001520572450805009,
      "loss": 0.4057,
      "num_input_tokens_seen": 449919,
      "step": 670
    },
    {
      "epoch": 0.24329159212880144,
      "grad_norm": 0.3819845914840698,
      "learning_rate": 0.00015134168157423971,
      "loss": 0.3951,
      "num_input_tokens_seen": 455612,
      "step": 680
    },
    {
      "epoch": 0.24686940966010734,
      "grad_norm": 0.3687816560268402,
      "learning_rate": 0.00015062611806797855,
      "loss": 0.4176,
      "num_input_tokens_seen": 461846,
      "step": 690
    },
    {
      "epoch": 0.2504472271914132,
      "grad_norm": 0.32070156931877136,
      "learning_rate": 0.00014991055456171735,
      "loss": 0.4111,
      "num_input_tokens_seen": 468333,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 2795,
  "num_input_tokens_seen": 468333,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 1.0531155302590464e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}