{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9827003787491043,
  "eval_steps": 200,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008189169822909202,
      "grad_norm": 4.80268669128418,
      "learning_rate": 0.0001,
      "loss": 1.6951,
      "step": 10
    },
    {
      "epoch": 0.016378339645818404,
      "grad_norm": 2.047800302505493,
      "learning_rate": 0.0001,
      "loss": 0.983,
      "step": 20
    },
    {
      "epoch": 0.024567509468727607,
      "grad_norm": 1.5396971702575684,
      "learning_rate": 0.0001,
      "loss": 0.9092,
      "step": 30
    },
    {
      "epoch": 0.03275667929163681,
      "grad_norm": 4.307969093322754,
      "learning_rate": 0.0001,
      "loss": 0.8544,
      "step": 40
    },
    {
      "epoch": 0.04094584911454601,
      "grad_norm": 2.1945383548736572,
      "learning_rate": 0.0001,
      "loss": 0.8015,
      "step": 50
    },
    {
      "epoch": 0.04913501893745521,
      "grad_norm": 1.5352895259857178,
      "learning_rate": 0.0001,
      "loss": 0.7917,
      "step": 60
    },
    {
      "epoch": 0.057324188760364415,
      "grad_norm": 1.9893757104873657,
      "learning_rate": 0.0001,
      "loss": 0.7561,
      "step": 70
    },
    {
      "epoch": 0.06551335858327362,
      "grad_norm": 1.067208170890808,
      "learning_rate": 0.0001,
      "loss": 0.7457,
      "step": 80
    },
    {
      "epoch": 0.07370252840618283,
      "grad_norm": 1.8355977535247803,
      "learning_rate": 0.0001,
      "loss": 0.7197,
      "step": 90
    },
    {
      "epoch": 0.08189169822909202,
      "grad_norm": 0.9938833713531494,
      "learning_rate": 0.0001,
      "loss": 0.6959,
      "step": 100
    },
    {
      "epoch": 0.09008086805200123,
      "grad_norm": 1.5569779872894287,
      "learning_rate": 0.0001,
      "loss": 0.6875,
      "step": 110
    },
    {
      "epoch": 0.09827003787491043,
      "grad_norm": 1.362318515777588,
      "learning_rate": 0.0001,
      "loss": 0.7031,
      "step": 120
    },
    {
      "epoch": 0.10645920769781964,
      "grad_norm": 0.9789265990257263,
      "learning_rate": 0.0001,
      "loss": 0.6744,
      "step": 130
    },
    {
      "epoch": 0.11464837752072883,
      "grad_norm": 0.9227413535118103,
      "learning_rate": 0.0001,
      "loss": 0.6496,
      "step": 140
    },
    {
      "epoch": 0.12283754734363804,
      "grad_norm": 1.0309714078903198,
      "learning_rate": 0.0001,
      "loss": 0.6365,
      "step": 150
    },
    {
      "epoch": 0.13102671716654724,
      "grad_norm": 1.2037794589996338,
      "learning_rate": 0.0001,
      "loss": 0.6629,
      "step": 160
    },
    {
      "epoch": 0.13921588698945644,
      "grad_norm": 0.8785035014152527,
      "learning_rate": 0.0001,
      "loss": 0.6462,
      "step": 170
    },
    {
      "epoch": 0.14740505681236565,
      "grad_norm": 1.5502973794937134,
      "learning_rate": 0.0001,
      "loss": 0.6146,
      "step": 180
    },
    {
      "epoch": 0.15559422663527486,
      "grad_norm": 0.9982532858848572,
      "learning_rate": 0.0001,
      "loss": 0.6205,
      "step": 190
    },
    {
      "epoch": 0.16378339645818404,
      "grad_norm": 1.0146996974945068,
      "learning_rate": 0.0001,
      "loss": 0.6107,
      "step": 200
    },
    {
      "epoch": 0.16378339645818404,
      "eval_loss": 0.5019610524177551,
      "eval_runtime": 993.1256,
      "eval_samples_per_second": 36.249,
      "eval_steps_per_second": 18.125,
      "step": 200
    },
    {
      "epoch": 0.17197256628109325,
      "grad_norm": 1.0556907653808594,
      "learning_rate": 0.0001,
      "loss": 0.6103,
      "step": 210
    },
    {
      "epoch": 0.18016173610400246,
      "grad_norm": 1.069365382194519,
      "learning_rate": 0.0001,
      "loss": 0.6309,
      "step": 220
    },
    {
      "epoch": 0.18835090592691167,
      "grad_norm": 1.2085084915161133,
      "learning_rate": 0.0001,
      "loss": 0.598,
      "step": 230
    },
    {
      "epoch": 0.19654007574982085,
      "grad_norm": 0.8124738931655884,
      "learning_rate": 0.0001,
      "loss": 0.603,
      "step": 240
    },
    {
      "epoch": 0.20472924557273006,
      "grad_norm": 1.032139778137207,
      "learning_rate": 0.0001,
      "loss": 0.611,
      "step": 250
    },
    {
      "epoch": 0.21291841539563927,
      "grad_norm": 0.8203685283660889,
      "learning_rate": 0.0001,
      "loss": 0.5709,
      "step": 260
    },
    {
      "epoch": 0.22110758521854848,
      "grad_norm": 0.7408131957054138,
      "learning_rate": 0.0001,
      "loss": 0.5753,
      "step": 270
    },
    {
      "epoch": 0.22929675504145766,
      "grad_norm": 0.858842134475708,
      "learning_rate": 0.0001,
      "loss": 0.5649,
      "step": 280
    },
    {
      "epoch": 0.23748592486436687,
      "grad_norm": 0.9077485799789429,
      "learning_rate": 0.0001,
      "loss": 0.5769,
      "step": 290
    },
    {
      "epoch": 0.24567509468727608,
      "grad_norm": 1.1604504585266113,
      "learning_rate": 0.0001,
      "loss": 0.5558,
      "step": 300
    },
    {
      "epoch": 0.2538642645101853,
      "grad_norm": 0.7758939266204834,
      "learning_rate": 0.0001,
      "loss": 0.5711,
      "step": 310
    },
    {
      "epoch": 0.26205343433309447,
      "grad_norm": 1.2495347261428833,
      "learning_rate": 0.0001,
      "loss": 0.5845,
      "step": 320
    },
    {
      "epoch": 0.2702426041560037,
      "grad_norm": 0.8986139297485352,
      "learning_rate": 0.0001,
      "loss": 0.5483,
      "step": 330
    },
    {
      "epoch": 0.2784317739789129,
      "grad_norm": 0.7849992513656616,
      "learning_rate": 0.0001,
      "loss": 0.5682,
      "step": 340
    },
    {
      "epoch": 0.28662094380182207,
      "grad_norm": 0.8479835987091064,
      "learning_rate": 0.0001,
      "loss": 0.5381,
      "step": 350
    },
    {
      "epoch": 0.2948101136247313,
      "grad_norm": 0.9730711579322815,
      "learning_rate": 0.0001,
      "loss": 0.5572,
      "step": 360
    },
    {
      "epoch": 0.3029992834476405,
      "grad_norm": 0.8130871653556824,
      "learning_rate": 0.0001,
      "loss": 0.5285,
      "step": 370
    },
    {
      "epoch": 0.3111884532705497,
      "grad_norm": 0.7159671783447266,
      "learning_rate": 0.0001,
      "loss": 0.529,
      "step": 380
    },
    {
      "epoch": 0.3193776230934589,
      "grad_norm": 0.7021393775939941,
      "learning_rate": 0.0001,
      "loss": 0.5371,
      "step": 390
    },
    {
      "epoch": 0.3275667929163681,
      "grad_norm": 0.9046493172645569,
      "learning_rate": 0.0001,
      "loss": 0.5412,
      "step": 400
    },
    {
      "epoch": 0.3275667929163681,
      "eval_loss": 0.43820247054100037,
      "eval_runtime": 1014.548,
      "eval_samples_per_second": 35.484,
      "eval_steps_per_second": 17.742,
      "step": 400
    },
    {
      "epoch": 0.3357559627392773,
      "grad_norm": 0.9188250303268433,
      "learning_rate": 0.0001,
      "loss": 0.5567,
      "step": 410
    },
    {
      "epoch": 0.3439451325621865,
      "grad_norm": 0.6707028150558472,
      "learning_rate": 0.0001,
      "loss": 0.5303,
      "step": 420
    },
    {
      "epoch": 0.3521343023850957,
      "grad_norm": 1.1012392044067383,
      "learning_rate": 0.0001,
      "loss": 0.5356,
      "step": 430
    },
    {
      "epoch": 0.3603234722080049,
      "grad_norm": 0.6614859104156494,
      "learning_rate": 0.0001,
      "loss": 0.5443,
      "step": 440
    },
    {
      "epoch": 0.3685126420309141,
      "grad_norm": 0.8753280639648438,
      "learning_rate": 0.0001,
      "loss": 0.5278,
      "step": 450
    },
    {
      "epoch": 0.37670181185382334,
      "grad_norm": 0.713115394115448,
      "learning_rate": 0.0001,
      "loss": 0.5344,
      "step": 460
    },
    {
      "epoch": 0.3848909816767325,
      "grad_norm": 1.034822940826416,
      "learning_rate": 0.0001,
      "loss": 0.511,
      "step": 470
    },
    {
      "epoch": 0.3930801514996417,
      "grad_norm": 0.7497478723526001,
      "learning_rate": 0.0001,
      "loss": 0.5143,
      "step": 480
    },
    {
      "epoch": 0.40126932132255094,
      "grad_norm": 0.9680531024932861,
      "learning_rate": 0.0001,
      "loss": 0.5372,
      "step": 490
    },
    {
      "epoch": 0.4094584911454601,
      "grad_norm": 0.6382943391799927,
      "learning_rate": 0.0001,
      "loss": 0.5242,
      "step": 500
    },
    {
      "epoch": 0.4176476609683693,
      "grad_norm": 0.7657376527786255,
      "learning_rate": 0.0001,
      "loss": 0.5125,
      "step": 510
    },
    {
      "epoch": 0.42583683079127854,
      "grad_norm": 0.9952341914176941,
      "learning_rate": 0.0001,
      "loss": 0.507,
      "step": 520
    },
    {
      "epoch": 0.4340260006141877,
      "grad_norm": 0.8375737071037292,
      "learning_rate": 0.0001,
      "loss": 0.5142,
      "step": 530
    },
    {
      "epoch": 0.44221517043709696,
      "grad_norm": 0.7849007844924927,
      "learning_rate": 0.0001,
      "loss": 0.5049,
      "step": 540
    },
    {
      "epoch": 0.45040434026000614,
      "grad_norm": 0.7818809151649475,
      "learning_rate": 0.0001,
      "loss": 0.4921,
      "step": 550
    },
    {
      "epoch": 0.4585935100829153,
      "grad_norm": 0.6086965203285217,
      "learning_rate": 0.0001,
      "loss": 0.5254,
      "step": 560
    },
    {
      "epoch": 0.46678267990582456,
      "grad_norm": 0.6038303971290588,
      "learning_rate": 0.0001,
      "loss": 0.5044,
      "step": 570
    },
    {
      "epoch": 0.47497184972873374,
      "grad_norm": 0.7107850313186646,
      "learning_rate": 0.0001,
      "loss": 0.5189,
      "step": 580
    },
    {
      "epoch": 0.483161019551643,
      "grad_norm": 0.7399956583976746,
      "learning_rate": 0.0001,
      "loss": 0.4814,
      "step": 590
    },
    {
      "epoch": 0.49135018937455216,
      "grad_norm": 0.7447919249534607,
      "learning_rate": 0.0001,
      "loss": 0.5273,
      "step": 600
    },
    {
      "epoch": 0.49135018937455216,
      "eval_loss": 0.41115716099739075,
      "eval_runtime": 974.1489,
      "eval_samples_per_second": 36.955,
      "eval_steps_per_second": 18.478,
      "step": 600
    },
    {
      "epoch": 0.49953935919746134,
      "grad_norm": 0.7186319231987,
      "learning_rate": 0.0001,
      "loss": 0.4964,
      "step": 610
    },
    {
      "epoch": 0.5077285290203706,
      "grad_norm": 0.6659027338027954,
      "learning_rate": 0.0001,
      "loss": 0.4813,
      "step": 620
    },
    {
      "epoch": 0.5159176988432798,
      "grad_norm": 0.8509200811386108,
      "learning_rate": 0.0001,
      "loss": 0.5007,
      "step": 630
    },
    {
      "epoch": 0.5241068686661889,
      "grad_norm": 0.7163340449333191,
      "learning_rate": 0.0001,
      "loss": 0.4918,
      "step": 640
    },
    {
      "epoch": 0.5322960384890981,
      "grad_norm": 0.6762372851371765,
      "learning_rate": 0.0001,
      "loss": 0.4721,
      "step": 650
    },
    {
      "epoch": 0.5404852083120074,
      "grad_norm": 0.741247832775116,
      "learning_rate": 0.0001,
      "loss": 0.5035,
      "step": 660
    },
    {
      "epoch": 0.5486743781349166,
      "grad_norm": 0.6757375001907349,
      "learning_rate": 0.0001,
      "loss": 0.5044,
      "step": 670
    },
    {
      "epoch": 0.5568635479578258,
      "grad_norm": 0.6605280637741089,
      "learning_rate": 0.0001,
      "loss": 0.5036,
      "step": 680
    },
    {
      "epoch": 0.565052717780735,
      "grad_norm": 0.7928522825241089,
      "learning_rate": 0.0001,
      "loss": 0.4884,
      "step": 690
    },
    {
      "epoch": 0.5732418876036441,
      "grad_norm": 0.7482662796974182,
      "learning_rate": 0.0001,
      "loss": 0.4831,
      "step": 700
    },
    {
      "epoch": 0.5814310574265534,
      "grad_norm": 0.7094814777374268,
      "learning_rate": 0.0001,
      "loss": 0.493,
      "step": 710
    },
    {
      "epoch": 0.5896202272494626,
      "grad_norm": 0.708988606929779,
      "learning_rate": 0.0001,
      "loss": 0.4878,
      "step": 720
    },
    {
      "epoch": 0.5978093970723718,
      "grad_norm": 0.7677808403968811,
      "learning_rate": 0.0001,
      "loss": 0.4819,
      "step": 730
    },
    {
      "epoch": 0.605998566895281,
      "grad_norm": 0.6716774702072144,
      "learning_rate": 0.0001,
      "loss": 0.505,
      "step": 740
    },
    {
      "epoch": 0.6141877367181902,
      "grad_norm": 0.6802059412002563,
      "learning_rate": 0.0001,
      "loss": 0.4612,
      "step": 750
    },
    {
      "epoch": 0.6223769065410995,
      "grad_norm": 0.7577608227729797,
      "learning_rate": 0.0001,
      "loss": 0.4814,
      "step": 760
    },
    {
      "epoch": 0.6305660763640086,
      "grad_norm": 0.6441067457199097,
      "learning_rate": 0.0001,
      "loss": 0.4838,
      "step": 770
    },
    {
      "epoch": 0.6387552461869178,
      "grad_norm": 0.666208028793335,
      "learning_rate": 0.0001,
      "loss": 0.4908,
      "step": 780
    },
    {
      "epoch": 0.646944416009827,
      "grad_norm": 0.7665196657180786,
      "learning_rate": 0.0001,
      "loss": 0.4716,
      "step": 790
    },
    {
      "epoch": 0.6551335858327362,
      "grad_norm": 0.8056005239486694,
      "learning_rate": 0.0001,
      "loss": 0.4717,
      "step": 800
    },
    {
      "epoch": 0.6551335858327362,
      "eval_loss": 0.41053226590156555,
      "eval_runtime": 952.7571,
      "eval_samples_per_second": 37.785,
      "eval_steps_per_second": 18.893,
      "step": 800
    },
    {
      "epoch": 0.6633227556556454,
      "grad_norm": 1.5036696195602417,
      "learning_rate": 0.0001,
      "loss": 0.4711,
      "step": 810
    },
    {
      "epoch": 0.6715119254785546,
      "grad_norm": 0.7547106146812439,
      "learning_rate": 0.0001,
      "loss": 0.476,
      "step": 820
    },
    {
      "epoch": 0.6797010953014638,
      "grad_norm": 0.7936639785766602,
      "learning_rate": 0.0001,
      "loss": 0.4762,
      "step": 830
    },
    {
      "epoch": 0.687890265124373,
      "grad_norm": 0.7227616310119629,
      "learning_rate": 0.0001,
      "loss": 0.4798,
      "step": 840
    },
    {
      "epoch": 0.6960794349472822,
      "grad_norm": 0.7741641402244568,
      "learning_rate": 0.0001,
      "loss": 0.4992,
      "step": 850
    },
    {
      "epoch": 0.7042686047701914,
      "grad_norm": 0.6723213791847229,
      "learning_rate": 0.0001,
      "loss": 0.4818,
      "step": 860
    },
    {
      "epoch": 0.7124577745931007,
      "grad_norm": 0.5631268620491028,
      "learning_rate": 0.0001,
      "loss": 0.481,
      "step": 870
    },
    {
      "epoch": 0.7206469444160098,
      "grad_norm": 0.7071460485458374,
      "learning_rate": 0.0001,
      "loss": 0.4744,
      "step": 880
    },
    {
      "epoch": 0.728836114238919,
      "grad_norm": 0.6503288745880127,
      "learning_rate": 0.0001,
      "loss": 0.4466,
      "step": 890
    },
    {
      "epoch": 0.7370252840618282,
      "grad_norm": 0.6489100456237793,
      "learning_rate": 0.0001,
      "loss": 0.4708,
      "step": 900
    },
    {
      "epoch": 0.7452144538847374,
      "grad_norm": 0.7342277765274048,
      "learning_rate": 0.0001,
      "loss": 0.4687,
      "step": 910
    },
    {
      "epoch": 0.7534036237076467,
      "grad_norm": 0.6502553224563599,
      "learning_rate": 0.0001,
      "loss": 0.4649,
      "step": 920
    },
    {
      "epoch": 0.7615927935305559,
      "grad_norm": 0.6611005663871765,
      "learning_rate": 0.0001,
      "loss": 0.4771,
      "step": 930
    },
    {
      "epoch": 0.769781963353465,
      "grad_norm": 0.5838377475738525,
      "learning_rate": 0.0001,
      "loss": 0.4671,
      "step": 940
    },
    {
      "epoch": 0.7779711331763742,
      "grad_norm": 0.6084617972373962,
      "learning_rate": 0.0001,
      "loss": 0.4701,
      "step": 950
    },
    {
      "epoch": 0.7861603029992834,
      "grad_norm": 0.6489084959030151,
      "learning_rate": 0.0001,
      "loss": 0.4586,
      "step": 960
    },
    {
      "epoch": 0.7943494728221927,
      "grad_norm": 0.6316090226173401,
      "learning_rate": 0.0001,
      "loss": 0.451,
      "step": 970
    },
    {
      "epoch": 0.8025386426451019,
      "grad_norm": 0.6724498271942139,
      "learning_rate": 0.0001,
      "loss": 0.4776,
      "step": 980
    },
    {
      "epoch": 0.8107278124680111,
      "grad_norm": 0.6327974796295166,
      "learning_rate": 0.0001,
      "loss": 0.4708,
      "step": 990
    },
    {
      "epoch": 0.8189169822909202,
      "grad_norm": 0.8041887879371643,
      "learning_rate": 0.0001,
      "loss": 0.4835,
      "step": 1000
    },
    {
      "epoch": 0.8189169822909202,
      "eval_loss": 0.39249786734580994,
      "eval_runtime": 953.0333,
      "eval_samples_per_second": 37.774,
      "eval_steps_per_second": 18.887,
      "step": 1000
    },
    {
      "epoch": 0.8271061521138294,
      "grad_norm": 0.7333071827888489,
      "learning_rate": 0.0001,
      "loss": 0.4662,
      "step": 1010
    },
    {
      "epoch": 0.8352953219367386,
      "grad_norm": 0.6036032438278198,
      "learning_rate": 0.0001,
      "loss": 0.449,
      "step": 1020
    },
    {
      "epoch": 0.8434844917596479,
      "grad_norm": 0.6087955236434937,
      "learning_rate": 0.0001,
      "loss": 0.4651,
      "step": 1030
    },
    {
      "epoch": 0.8516736615825571,
      "grad_norm": 0.8231128454208374,
      "learning_rate": 0.0001,
      "loss": 0.4672,
      "step": 1040
    },
    {
      "epoch": 0.8598628314054663,
      "grad_norm": 0.6176358461380005,
      "learning_rate": 0.0001,
      "loss": 0.4616,
      "step": 1050
    },
    {
      "epoch": 0.8680520012283754,
      "grad_norm": 0.5654678344726562,
      "learning_rate": 0.0001,
      "loss": 0.437,
      "step": 1060
    },
    {
      "epoch": 0.8762411710512846,
      "grad_norm": 0.6934413909912109,
      "learning_rate": 0.0001,
      "loss": 0.4302,
      "step": 1070
    },
    {
      "epoch": 0.8844303408741939,
      "grad_norm": 0.6048303842544556,
      "learning_rate": 0.0001,
      "loss": 0.4584,
      "step": 1080
    },
    {
      "epoch": 0.8926195106971031,
      "grad_norm": 0.6487530469894409,
      "learning_rate": 0.0001,
      "loss": 0.4647,
      "step": 1090
    },
    {
      "epoch": 0.9008086805200123,
      "grad_norm": 0.6674748659133911,
      "learning_rate": 0.0001,
      "loss": 0.467,
      "step": 1100
    },
    {
      "epoch": 0.9089978503429215,
      "grad_norm": 0.6509521007537842,
      "learning_rate": 0.0001,
      "loss": 0.4525,
      "step": 1110
    },
    {
      "epoch": 0.9171870201658306,
      "grad_norm": 0.6949372291564941,
      "learning_rate": 0.0001,
      "loss": 0.4663,
      "step": 1120
    },
    {
      "epoch": 0.9253761899887399,
      "grad_norm": 0.7340756058692932,
      "learning_rate": 0.0001,
      "loss": 0.4297,
      "step": 1130
    },
    {
      "epoch": 0.9335653598116491,
      "grad_norm": 0.5543187856674194,
      "learning_rate": 0.0001,
      "loss": 0.4606,
      "step": 1140
    },
    {
      "epoch": 0.9417545296345583,
      "grad_norm": 0.6061782836914062,
      "learning_rate": 0.0001,
      "loss": 0.4589,
      "step": 1150
    },
    {
      "epoch": 0.9499436994574675,
      "grad_norm": 0.6638914942741394,
      "learning_rate": 0.0001,
      "loss": 0.4252,
      "step": 1160
    },
    {
      "epoch": 0.9581328692803767,
      "grad_norm": 0.5913025736808777,
      "learning_rate": 0.0001,
      "loss": 0.44,
      "step": 1170
    },
    {
      "epoch": 0.966322039103286,
      "grad_norm": 0.5672889947891235,
      "learning_rate": 0.0001,
      "loss": 0.4659,
      "step": 1180
    },
    {
      "epoch": 0.9745112089261951,
      "grad_norm": 0.5614264607429504,
      "learning_rate": 0.0001,
      "loss": 0.4471,
      "step": 1190
    },
    {
      "epoch": 0.9827003787491043,
      "grad_norm": 0.5809562802314758,
      "learning_rate": 0.0001,
      "loss": 0.4288,
      "step": 1200
    },
    {
      "epoch": 0.9827003787491043,
      "eval_loss": 0.37333595752716064,
      "eval_runtime": 961.0219,
      "eval_samples_per_second": 37.46,
      "eval_steps_per_second": 18.73,
      "step": 1200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1221,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.304264713469952e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}