{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9973206311402203,
  "eval_steps": 500,
  "global_step": 1257,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023816612086930634,
      "grad_norm": 10.820662608896704,
      "learning_rate": 5e-06,
      "loss": 0.7962,
      "step": 10
    },
    {
      "epoch": 0.04763322417386127,
      "grad_norm": 1.3002290223711226,
      "learning_rate": 5e-06,
      "loss": 0.6506,
      "step": 20
    },
    {
      "epoch": 0.0714498362607919,
      "grad_norm": 2.274364660793754,
      "learning_rate": 5e-06,
      "loss": 0.5997,
      "step": 30
    },
    {
      "epoch": 0.09526644834772253,
      "grad_norm": 0.91227766008184,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 40
    },
    {
      "epoch": 0.11908306043465317,
      "grad_norm": 0.8965545265977676,
      "learning_rate": 5e-06,
      "loss": 0.5522,
      "step": 50
    },
    {
      "epoch": 0.1428996725215838,
      "grad_norm": 0.7367789232478065,
      "learning_rate": 5e-06,
      "loss": 0.5413,
      "step": 60
    },
    {
      "epoch": 0.16671628460851443,
      "grad_norm": 1.959786214629393,
      "learning_rate": 5e-06,
      "loss": 0.5254,
      "step": 70
    },
    {
      "epoch": 0.19053289669544507,
      "grad_norm": 1.1527597962719172,
      "learning_rate": 5e-06,
      "loss": 0.5263,
      "step": 80
    },
    {
      "epoch": 0.21434950878237571,
      "grad_norm": 0.8809156142645043,
      "learning_rate": 5e-06,
      "loss": 0.5139,
      "step": 90
    },
    {
      "epoch": 0.23816612086930633,
      "grad_norm": 0.6829627408546641,
      "learning_rate": 5e-06,
      "loss": 0.5047,
      "step": 100
    },
    {
      "epoch": 0.261982732956237,
      "grad_norm": 0.5878115863496259,
      "learning_rate": 5e-06,
      "loss": 0.4974,
      "step": 110
    },
    {
      "epoch": 0.2857993450431676,
      "grad_norm": 0.7963943568799848,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 120
    },
    {
      "epoch": 0.30961595713009826,
      "grad_norm": 0.8168312496362183,
      "learning_rate": 5e-06,
      "loss": 0.4909,
      "step": 130
    },
    {
      "epoch": 0.33343256921702885,
      "grad_norm": 0.5860607753114995,
      "learning_rate": 5e-06,
      "loss": 0.4881,
      "step": 140
    },
    {
      "epoch": 0.3572491813039595,
      "grad_norm": 0.6645019696194568,
      "learning_rate": 5e-06,
      "loss": 0.4891,
      "step": 150
    },
    {
      "epoch": 0.38106579339089014,
      "grad_norm": 1.1349953393684589,
      "learning_rate": 5e-06,
      "loss": 0.4886,
      "step": 160
    },
    {
      "epoch": 0.4048824054778208,
      "grad_norm": 0.842239450444899,
      "learning_rate": 5e-06,
      "loss": 0.486,
      "step": 170
    },
    {
      "epoch": 0.42869901756475143,
      "grad_norm": 0.8029347648800014,
      "learning_rate": 5e-06,
      "loss": 0.4794,
      "step": 180
    },
    {
      "epoch": 0.45251562965168207,
      "grad_norm": 0.7453080201307035,
      "learning_rate": 5e-06,
      "loss": 0.4779,
      "step": 190
    },
    {
      "epoch": 0.47633224173861266,
      "grad_norm": 0.7560106227106046,
      "learning_rate": 5e-06,
      "loss": 0.4755,
      "step": 200
    },
    {
      "epoch": 0.5001488538255433,
      "grad_norm": 0.6803104426449306,
      "learning_rate": 5e-06,
      "loss": 0.4738,
      "step": 210
    },
    {
      "epoch": 0.523965465912474,
      "grad_norm": 0.5983251461773578,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 220
    },
    {
      "epoch": 0.5477820779994046,
      "grad_norm": 0.9213163769902233,
      "learning_rate": 5e-06,
      "loss": 0.466,
      "step": 230
    },
    {
      "epoch": 0.5715986900863352,
      "grad_norm": 0.7194449280323925,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 240
    },
    {
      "epoch": 0.5954153021732659,
      "grad_norm": 0.5686308646341993,
      "learning_rate": 5e-06,
      "loss": 0.472,
      "step": 250
    },
    {
      "epoch": 0.6192319142601965,
      "grad_norm": 1.0813640818776593,
      "learning_rate": 5e-06,
      "loss": 0.4661,
      "step": 260
    },
    {
      "epoch": 0.6430485263471272,
      "grad_norm": 0.7358980285755272,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 270
    },
    {
      "epoch": 0.6668651384340577,
      "grad_norm": 0.6604585093191498,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 280
    },
    {
      "epoch": 0.6906817505209883,
      "grad_norm": 0.7044805358584626,
      "learning_rate": 5e-06,
      "loss": 0.4627,
      "step": 290
    },
    {
      "epoch": 0.714498362607919,
      "grad_norm": 0.7424204761656356,
      "learning_rate": 5e-06,
      "loss": 0.4597,
      "step": 300
    },
    {
      "epoch": 0.7383149746948496,
      "grad_norm": 0.6489446693829575,
      "learning_rate": 5e-06,
      "loss": 0.4596,
      "step": 310
    },
    {
      "epoch": 0.7621315867817803,
      "grad_norm": 0.7368542344749955,
      "learning_rate": 5e-06,
      "loss": 0.4645,
      "step": 320
    },
    {
      "epoch": 0.7859481988687109,
      "grad_norm": 0.7920469169588614,
      "learning_rate": 5e-06,
      "loss": 0.4532,
      "step": 330
    },
    {
      "epoch": 0.8097648109556416,
      "grad_norm": 0.4836289408504863,
      "learning_rate": 5e-06,
      "loss": 0.4546,
      "step": 340
    },
    {
      "epoch": 0.8335814230425722,
      "grad_norm": 0.4793593414506298,
      "learning_rate": 5e-06,
      "loss": 0.455,
      "step": 350
    },
    {
      "epoch": 0.8573980351295029,
      "grad_norm": 0.6323515901480585,
      "learning_rate": 5e-06,
      "loss": 0.4562,
      "step": 360
    },
    {
      "epoch": 0.8812146472164335,
      "grad_norm": 0.6239832843962634,
      "learning_rate": 5e-06,
      "loss": 0.4613,
      "step": 370
    },
    {
      "epoch": 0.9050312593033641,
      "grad_norm": 0.545469740506038,
      "learning_rate": 5e-06,
      "loss": 0.4505,
      "step": 380
    },
    {
      "epoch": 0.9288478713902947,
      "grad_norm": 0.7122693018169797,
      "learning_rate": 5e-06,
      "loss": 0.4548,
      "step": 390
    },
    {
      "epoch": 0.9526644834772253,
      "grad_norm": 0.7239717244861085,
      "learning_rate": 5e-06,
      "loss": 0.4482,
      "step": 400
    },
    {
      "epoch": 0.976481095564156,
      "grad_norm": 0.8780808883400644,
      "learning_rate": 5e-06,
      "loss": 0.4531,
      "step": 410
    },
    {
      "epoch": 0.9979160464423936,
      "eval_loss": 0.45424818992614746,
      "eval_runtime": 286.0837,
      "eval_samples_per_second": 39.551,
      "eval_steps_per_second": 0.619,
      "step": 419
    },
    {
      "epoch": 1.0020839535576065,
      "grad_norm": 1.5666613895216177,
      "learning_rate": 5e-06,
      "loss": 0.4859,
      "step": 420
    },
    {
      "epoch": 1.025900565644537,
      "grad_norm": 0.8242103660038579,
      "learning_rate": 5e-06,
      "loss": 0.4102,
      "step": 430
    },
    {
      "epoch": 1.0497171777314678,
      "grad_norm": 0.7452119219276494,
      "learning_rate": 5e-06,
      "loss": 0.4092,
      "step": 440
    },
    {
      "epoch": 1.0735337898183983,
      "grad_norm": 0.6691470793599864,
      "learning_rate": 5e-06,
      "loss": 0.4052,
      "step": 450
    },
    {
      "epoch": 1.097350401905329,
      "grad_norm": 0.7840952133237613,
      "learning_rate": 5e-06,
      "loss": 0.4105,
      "step": 460
    },
    {
      "epoch": 1.1211670139922596,
      "grad_norm": 0.6028706220060683,
      "learning_rate": 5e-06,
      "loss": 0.4084,
      "step": 470
    },
    {
      "epoch": 1.1449836260791901,
      "grad_norm": 0.6295729577533348,
      "learning_rate": 5e-06,
      "loss": 0.411,
      "step": 480
    },
    {
      "epoch": 1.1688002381661209,
      "grad_norm": 0.5614428880763974,
      "learning_rate": 5e-06,
      "loss": 0.4035,
      "step": 490
    },
    {
      "epoch": 1.1926168502530514,
      "grad_norm": 0.7354574620421201,
      "learning_rate": 5e-06,
      "loss": 0.4128,
      "step": 500
    },
    {
      "epoch": 1.2164334623399822,
      "grad_norm": 0.6533242864715311,
      "learning_rate": 5e-06,
      "loss": 0.409,
      "step": 510
    },
    {
      "epoch": 1.2402500744269127,
      "grad_norm": 0.5341268826400728,
      "learning_rate": 5e-06,
      "loss": 0.4069,
      "step": 520
    },
    {
      "epoch": 1.2640666865138435,
      "grad_norm": 0.595790957629028,
      "learning_rate": 5e-06,
      "loss": 0.403,
      "step": 530
    },
    {
      "epoch": 1.287883298600774,
      "grad_norm": 0.5757459346899625,
      "learning_rate": 5e-06,
      "loss": 0.4043,
      "step": 540
    },
    {
      "epoch": 1.3116999106877048,
      "grad_norm": 0.6014475432063849,
      "learning_rate": 5e-06,
      "loss": 0.4063,
      "step": 550
    },
    {
      "epoch": 1.3355165227746353,
      "grad_norm": 0.6816804823593294,
      "learning_rate": 5e-06,
      "loss": 0.4054,
      "step": 560
    },
    {
      "epoch": 1.3593331348615658,
      "grad_norm": 0.8369295577084369,
      "learning_rate": 5e-06,
      "loss": 0.4038,
      "step": 570
    },
    {
      "epoch": 1.3831497469484966,
      "grad_norm": 0.5774046033105074,
      "learning_rate": 5e-06,
      "loss": 0.4041,
      "step": 580
    },
    {
      "epoch": 1.4069663590354273,
      "grad_norm": 0.6188803841652969,
      "learning_rate": 5e-06,
      "loss": 0.4064,
      "step": 590
    },
    {
      "epoch": 1.4307829711223579,
      "grad_norm": 0.6067419957695976,
      "learning_rate": 5e-06,
      "loss": 0.3998,
      "step": 600
    },
    {
      "epoch": 1.4545995832092884,
      "grad_norm": 0.7114287172431103,
      "learning_rate": 5e-06,
      "loss": 0.4024,
      "step": 610
    },
    {
      "epoch": 1.4784161952962191,
      "grad_norm": 0.6126178425690488,
      "learning_rate": 5e-06,
      "loss": 0.4026,
      "step": 620
    },
    {
      "epoch": 1.50223280738315,
      "grad_norm": 0.5281312737413801,
      "learning_rate": 5e-06,
      "loss": 0.4027,
      "step": 630
    },
    {
      "epoch": 1.5260494194700804,
      "grad_norm": 0.7216431853686169,
      "learning_rate": 5e-06,
      "loss": 0.4054,
      "step": 640
    },
    {
      "epoch": 1.549866031557011,
      "grad_norm": 0.6037953128159437,
      "learning_rate": 5e-06,
      "loss": 0.402,
      "step": 650
    },
    {
      "epoch": 1.5736826436439415,
      "grad_norm": 0.7237089947239425,
      "learning_rate": 5e-06,
      "loss": 0.3977,
      "step": 660
    },
    {
      "epoch": 1.5974992557308723,
      "grad_norm": 0.6225585837795767,
      "learning_rate": 5e-06,
      "loss": 0.3986,
      "step": 670
    },
    {
      "epoch": 1.621315867817803,
      "grad_norm": 0.6880389181478974,
      "learning_rate": 5e-06,
      "loss": 0.4037,
      "step": 680
    },
    {
      "epoch": 1.6451324799047335,
      "grad_norm": 0.6033306584926863,
      "learning_rate": 5e-06,
      "loss": 0.4022,
      "step": 690
    },
    {
      "epoch": 1.668949091991664,
      "grad_norm": 0.635681818377172,
      "learning_rate": 5e-06,
      "loss": 0.4068,
      "step": 700
    },
    {
      "epoch": 1.6927657040785948,
      "grad_norm": 0.6212447265932675,
      "learning_rate": 5e-06,
      "loss": 0.4003,
      "step": 710
    },
    {
      "epoch": 1.7165823161655256,
      "grad_norm": 0.8760196584827,
      "learning_rate": 5e-06,
      "loss": 0.3978,
      "step": 720
    },
    {
      "epoch": 1.7403989282524561,
      "grad_norm": 0.6660720739374277,
      "learning_rate": 5e-06,
      "loss": 0.4004,
      "step": 730
    },
    {
      "epoch": 1.7642155403393867,
      "grad_norm": 0.6326799745725241,
      "learning_rate": 5e-06,
      "loss": 0.4007,
      "step": 740
    },
    {
      "epoch": 1.7880321524263174,
      "grad_norm": 0.6030163934725129,
      "learning_rate": 5e-06,
      "loss": 0.4011,
      "step": 750
    },
    {
      "epoch": 1.811848764513248,
      "grad_norm": 0.6024754641341044,
      "learning_rate": 5e-06,
      "loss": 0.3941,
      "step": 760
    },
    {
      "epoch": 1.8356653766001787,
      "grad_norm": 0.5552872150124285,
      "learning_rate": 5e-06,
      "loss": 0.4042,
      "step": 770
    },
    {
      "epoch": 1.8594819886871092,
      "grad_norm": 0.5054694344878702,
      "learning_rate": 5e-06,
      "loss": 0.4029,
      "step": 780
    },
    {
      "epoch": 1.8832986007740398,
      "grad_norm": 0.7189726869611571,
      "learning_rate": 5e-06,
      "loss": 0.3992,
      "step": 790
    },
    {
      "epoch": 1.9071152128609705,
      "grad_norm": 0.5495927800255059,
      "learning_rate": 5e-06,
      "loss": 0.3969,
      "step": 800
    },
    {
      "epoch": 1.9309318249479013,
      "grad_norm": 0.5757953006798125,
      "learning_rate": 5e-06,
      "loss": 0.3995,
      "step": 810
    },
    {
      "epoch": 1.9547484370348318,
      "grad_norm": 0.5635263667269701,
      "learning_rate": 5e-06,
      "loss": 0.402,
      "step": 820
    },
    {
      "epoch": 1.9785650491217623,
      "grad_norm": 0.6248661080671392,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 830
    },
    {
      "epoch": 1.997618338791307,
      "eval_loss": 0.43693724274635315,
      "eval_runtime": 286.32,
      "eval_samples_per_second": 39.519,
      "eval_steps_per_second": 0.618,
      "step": 838
    },
    {
      "epoch": 2.004167907115213,
      "grad_norm": 0.8252136402016477,
      "learning_rate": 5e-06,
      "loss": 0.4321,
      "step": 840
    },
    {
      "epoch": 2.0279845192021435,
      "grad_norm": 0.8217614405447083,
      "learning_rate": 5e-06,
      "loss": 0.3538,
      "step": 850
    },
    {
      "epoch": 2.051801131289074,
      "grad_norm": 0.597126610910981,
      "learning_rate": 5e-06,
      "loss": 0.353,
      "step": 860
    },
    {
      "epoch": 2.0756177433760046,
      "grad_norm": 0.5891946978445731,
      "learning_rate": 5e-06,
      "loss": 0.3476,
      "step": 870
    },
    {
      "epoch": 2.0994343554629356,
      "grad_norm": 0.7349012751558448,
      "learning_rate": 5e-06,
      "loss": 0.3513,
      "step": 880
    },
    {
      "epoch": 2.123250967549866,
      "grad_norm": 0.6562744496253617,
      "learning_rate": 5e-06,
      "loss": 0.352,
      "step": 890
    },
    {
      "epoch": 2.1470675796367966,
      "grad_norm": 0.7348610922149896,
      "learning_rate": 5e-06,
      "loss": 0.3509,
      "step": 900
    },
    {
      "epoch": 2.170884191723727,
      "grad_norm": 0.5550207440255053,
      "learning_rate": 5e-06,
      "loss": 0.3517,
      "step": 910
    },
    {
      "epoch": 2.194700803810658,
      "grad_norm": 0.7725877741803382,
      "learning_rate": 5e-06,
      "loss": 0.3547,
      "step": 920
    },
    {
      "epoch": 2.2185174158975887,
      "grad_norm": 0.7254370201802991,
      "learning_rate": 5e-06,
      "loss": 0.3513,
      "step": 930
    },
    {
      "epoch": 2.242334027984519,
      "grad_norm": 0.7099191501450315,
      "learning_rate": 5e-06,
      "loss": 0.3534,
      "step": 940
    },
    {
      "epoch": 2.2661506400714497,
      "grad_norm": 0.6217727164056416,
      "learning_rate": 5e-06,
      "loss": 0.3525,
      "step": 950
    },
    {
      "epoch": 2.2899672521583803,
      "grad_norm": 0.7759463308703756,
      "learning_rate": 5e-06,
      "loss": 0.3561,
      "step": 960
    },
    {
      "epoch": 2.3137838642453112,
      "grad_norm": 0.8023649875600256,
      "learning_rate": 5e-06,
      "loss": 0.3574,
      "step": 970
    },
    {
      "epoch": 2.3376004763322418,
      "grad_norm": 0.6363742954254966,
      "learning_rate": 5e-06,
      "loss": 0.3568,
      "step": 980
    },
    {
      "epoch": 2.3614170884191723,
      "grad_norm": 0.6522324898510586,
      "learning_rate": 5e-06,
      "loss": 0.3545,
      "step": 990
    },
    {
      "epoch": 2.385233700506103,
      "grad_norm": 0.6816643137692279,
      "learning_rate": 5e-06,
      "loss": 0.3503,
      "step": 1000
    },
    {
      "epoch": 2.409050312593034,
      "grad_norm": 0.616355784268503,
      "learning_rate": 5e-06,
      "loss": 0.3539,
      "step": 1010
    },
    {
      "epoch": 2.4328669246799643,
      "grad_norm": 0.8616495256742727,
      "learning_rate": 5e-06,
      "loss": 0.3567,
      "step": 1020
    },
    {
      "epoch": 2.456683536766895,
      "grad_norm": 0.6281577543660147,
      "learning_rate": 5e-06,
      "loss": 0.355,
      "step": 1030
    },
    {
      "epoch": 2.4805001488538254,
      "grad_norm": 0.5605730765386269,
      "learning_rate": 5e-06,
      "loss": 0.3551,
      "step": 1040
    },
    {
      "epoch": 2.504316760940756,
      "grad_norm": 0.6217913711967288,
      "learning_rate": 5e-06,
      "loss": 0.3552,
      "step": 1050
    },
    {
      "epoch": 2.528133373027687,
      "grad_norm": 0.6599048002895368,
      "learning_rate": 5e-06,
      "loss": 0.3532,
      "step": 1060
    },
    {
      "epoch": 2.5519499851146175,
      "grad_norm": 0.7340133449366499,
      "learning_rate": 5e-06,
      "loss": 0.3546,
      "step": 1070
    },
    {
      "epoch": 2.575766597201548,
      "grad_norm": 0.7470486435804491,
      "learning_rate": 5e-06,
      "loss": 0.356,
      "step": 1080
    },
    {
      "epoch": 2.599583209288479,
      "grad_norm": 0.5596330861321896,
      "learning_rate": 5e-06,
      "loss": 0.3593,
      "step": 1090
    },
    {
      "epoch": 2.6233998213754095,
      "grad_norm": 0.655258490698248,
      "learning_rate": 5e-06,
      "loss": 0.3574,
      "step": 1100
    },
    {
      "epoch": 2.64721643346234,
      "grad_norm": 0.6634626122990018,
      "learning_rate": 5e-06,
      "loss": 0.3582,
      "step": 1110
    },
    {
      "epoch": 2.6710330455492706,
      "grad_norm": 0.6875550380429598,
      "learning_rate": 5e-06,
      "loss": 0.3567,
      "step": 1120
    },
    {
      "epoch": 2.694849657636201,
      "grad_norm": 0.6775433440528874,
      "learning_rate": 5e-06,
      "loss": 0.3574,
      "step": 1130
    },
    {
      "epoch": 2.7186662697231316,
      "grad_norm": 0.6304790171059349,
      "learning_rate": 5e-06,
      "loss": 0.3547,
      "step": 1140
    },
    {
      "epoch": 2.7424828818100626,
      "grad_norm": 0.6868875377983221,
      "learning_rate": 5e-06,
      "loss": 0.3547,
      "step": 1150
    },
    {
      "epoch": 2.766299493896993,
      "grad_norm": 0.8782114193263775,
      "learning_rate": 5e-06,
      "loss": 0.3586,
      "step": 1160
    },
    {
      "epoch": 2.7901161059839237,
      "grad_norm": 0.6003211481767972,
      "learning_rate": 5e-06,
      "loss": 0.3498,
      "step": 1170
    },
    {
      "epoch": 2.8139327180708547,
      "grad_norm": 0.6181739427734269,
      "learning_rate": 5e-06,
      "loss": 0.3611,
      "step": 1180
    },
    {
      "epoch": 2.837749330157785,
      "grad_norm": 0.5812515280780504,
      "learning_rate": 5e-06,
      "loss": 0.3593,
      "step": 1190
    },
    {
      "epoch": 2.8615659422447157,
      "grad_norm": 0.6647885239726261,
      "learning_rate": 5e-06,
      "loss": 0.357,
      "step": 1200
    },
    {
      "epoch": 2.8853825543316463,
      "grad_norm": 1.1264669697440912,
      "learning_rate": 5e-06,
      "loss": 0.356,
      "step": 1210
    },
    {
      "epoch": 2.909199166418577,
      "grad_norm": 0.7668811596236461,
      "learning_rate": 5e-06,
      "loss": 0.357,
      "step": 1220
    },
    {
      "epoch": 2.9330157785055073,
      "grad_norm": 0.5719772302769721,
      "learning_rate": 5e-06,
      "loss": 0.3531,
      "step": 1230
    },
    {
      "epoch": 2.9568323905924383,
      "grad_norm": 0.6110386348906062,
      "learning_rate": 5e-06,
      "loss": 0.3583,
      "step": 1240
    },
    {
      "epoch": 2.980649002679369,
      "grad_norm": 0.5843814268513303,
      "learning_rate": 5e-06,
      "loss": 0.3539,
      "step": 1250
    },
    {
      "epoch": 2.9973206311402203,
      "eval_loss": 0.4348444640636444,
      "eval_runtime": 294.9931,
      "eval_samples_per_second": 38.357,
      "eval_steps_per_second": 0.6,
      "step": 1257
    },
    {
      "epoch": 2.9973206311402203,
      "step": 1257,
      "total_flos": 2105312437862400.0,
      "train_loss": 0.41854361285268077,
      "train_runtime": 41355.0058,
      "train_samples_per_second": 15.594,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 1257,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2105312437862400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}