{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.949317738791423,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01949317738791423,
      "grad_norm": 9.292141914367676,
      "learning_rate": 4.967511371020143e-05,
      "loss": 6.2548,
      "step": 10
    },
    {
      "epoch": 0.03898635477582846,
      "grad_norm": 7.766495227813721,
      "learning_rate": 4.935022742040286e-05,
      "loss": 5.0175,
      "step": 20
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 6.4375128746032715,
      "learning_rate": 4.902534113060429e-05,
      "loss": 4.59,
      "step": 30
    },
    {
      "epoch": 0.07797270955165692,
      "grad_norm": 7.395759105682373,
      "learning_rate": 4.8700454840805724e-05,
      "loss": 4.2891,
      "step": 40
    },
    {
      "epoch": 0.09746588693957114,
      "grad_norm": 5.542599678039551,
      "learning_rate": 4.837556855100715e-05,
      "loss": 4.1904,
      "step": 50
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 8.749999046325684,
      "learning_rate": 4.805068226120858e-05,
      "loss": 4.1512,
      "step": 60
    },
    {
      "epoch": 0.1364522417153996,
      "grad_norm": 6.6702446937561035,
      "learning_rate": 4.772579597141001e-05,
      "loss": 3.9695,
      "step": 70
    },
    {
      "epoch": 0.15594541910331383,
      "grad_norm": 13.8934326171875,
      "learning_rate": 4.740090968161144e-05,
      "loss": 3.9657,
      "step": 80
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 15.161931037902832,
      "learning_rate": 4.707602339181287e-05,
      "loss": 3.9312,
      "step": 90
    },
    {
      "epoch": 0.1949317738791423,
      "grad_norm": 8.096311569213867,
      "learning_rate": 4.67511371020143e-05,
      "loss": 3.9407,
      "step": 100
    },
    {
      "epoch": 0.21442495126705652,
      "grad_norm": 6.077565670013428,
      "learning_rate": 4.642625081221573e-05,
      "loss": 3.7438,
      "step": 110
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 5.909548282623291,
      "learning_rate": 4.610136452241716e-05,
      "loss": 3.8495,
      "step": 120
    },
    {
      "epoch": 0.253411306042885,
      "grad_norm": 6.919253349304199,
      "learning_rate": 4.577647823261859e-05,
      "loss": 3.8178,
      "step": 130
    },
    {
      "epoch": 0.2729044834307992,
      "grad_norm": 5.3416218757629395,
      "learning_rate": 4.545159194282001e-05,
      "loss": 3.6388,
      "step": 140
    },
    {
      "epoch": 0.29239766081871343,
      "grad_norm": 6.484707832336426,
      "learning_rate": 4.512670565302144e-05,
      "loss": 3.8361,
      "step": 150
    },
    {
      "epoch": 0.31189083820662766,
      "grad_norm": 6.068100929260254,
      "learning_rate": 4.480181936322287e-05,
      "loss": 3.7164,
      "step": 160
    },
    {
      "epoch": 0.3313840155945419,
      "grad_norm": 6.298447608947754,
      "learning_rate": 4.4476933073424304e-05,
      "loss": 3.6589,
      "step": 170
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 4.752441883087158,
      "learning_rate": 4.4152046783625734e-05,
      "loss": 3.7328,
      "step": 180
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 5.050961971282959,
      "learning_rate": 4.3827160493827164e-05,
      "loss": 3.7162,
      "step": 190
    },
    {
      "epoch": 0.3898635477582846,
      "grad_norm": 4.73190975189209,
      "learning_rate": 4.3502274204028594e-05,
      "loss": 3.6748,
      "step": 200
    },
    {
      "epoch": 0.4093567251461988,
      "grad_norm": 10.872115135192871,
      "learning_rate": 4.3177387914230025e-05,
      "loss": 3.7618,
      "step": 210
    },
    {
      "epoch": 0.42884990253411304,
      "grad_norm": 6.119602680206299,
      "learning_rate": 4.285250162443145e-05,
      "loss": 3.747,
      "step": 220
    },
    {
      "epoch": 0.44834307992202727,
      "grad_norm": 5.332015514373779,
      "learning_rate": 4.252761533463288e-05,
      "loss": 3.6214,
      "step": 230
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 5.08021354675293,
      "learning_rate": 4.220272904483431e-05,
      "loss": 3.5122,
      "step": 240
    },
    {
      "epoch": 0.4873294346978557,
      "grad_norm": 4.609364986419678,
      "learning_rate": 4.187784275503574e-05,
      "loss": 3.5281,
      "step": 250
    },
    {
      "epoch": 0.50682261208577,
      "grad_norm": 24.73488998413086,
      "learning_rate": 4.155295646523717e-05,
      "loss": 3.7142,
      "step": 260
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 5.869173526763916,
      "learning_rate": 4.12280701754386e-05,
      "loss": 3.577,
      "step": 270
    },
    {
      "epoch": 0.5458089668615984,
      "grad_norm": 5.6849470138549805,
      "learning_rate": 4.090318388564003e-05,
      "loss": 3.6146,
      "step": 280
    },
    {
      "epoch": 0.5653021442495126,
      "grad_norm": 5.919517517089844,
      "learning_rate": 4.057829759584146e-05,
      "loss": 3.5417,
      "step": 290
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 5.177787780761719,
      "learning_rate": 4.025341130604289e-05,
      "loss": 3.5453,
      "step": 300
    },
    {
      "epoch": 0.6042884990253411,
      "grad_norm": 5.569265842437744,
      "learning_rate": 3.9928525016244314e-05,
      "loss": 3.5203,
      "step": 310
    },
    {
      "epoch": 0.6237816764132553,
      "grad_norm": 6.63994026184082,
      "learning_rate": 3.9603638726445744e-05,
      "loss": 3.5504,
      "step": 320
    },
    {
      "epoch": 0.6432748538011696,
      "grad_norm": 5.785546779632568,
      "learning_rate": 3.9278752436647174e-05,
      "loss": 3.5587,
      "step": 330
    },
    {
      "epoch": 0.6627680311890838,
      "grad_norm": 5.489815711975098,
      "learning_rate": 3.8953866146848605e-05,
      "loss": 3.5612,
      "step": 340
    },
    {
      "epoch": 0.682261208576998,
      "grad_norm": 4.650988578796387,
      "learning_rate": 3.8628979857050035e-05,
      "loss": 3.5062,
      "step": 350
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 5.7823872566223145,
      "learning_rate": 3.8304093567251465e-05,
      "loss": 3.5819,
      "step": 360
    },
    {
      "epoch": 0.7212475633528265,
      "grad_norm": 7.364371299743652,
      "learning_rate": 3.7979207277452896e-05,
      "loss": 3.5845,
      "step": 370
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 6.099256992340088,
      "learning_rate": 3.7654320987654326e-05,
      "loss": 3.5787,
      "step": 380
    },
    {
      "epoch": 0.7602339181286549,
      "grad_norm": 5.115094184875488,
      "learning_rate": 3.7329434697855756e-05,
      "loss": 3.5901,
      "step": 390
    },
    {
      "epoch": 0.7797270955165692,
      "grad_norm": 5.4442830085754395,
      "learning_rate": 3.700454840805718e-05,
      "loss": 3.4565,
      "step": 400
    },
    {
      "epoch": 0.7992202729044834,
      "grad_norm": 6.6567816734313965,
      "learning_rate": 3.667966211825861e-05,
      "loss": 3.5481,
      "step": 410
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 5.831213474273682,
      "learning_rate": 3.635477582846004e-05,
      "loss": 3.4274,
      "step": 420
    },
    {
      "epoch": 0.8382066276803118,
      "grad_norm": 5.754021167755127,
      "learning_rate": 3.602988953866147e-05,
      "loss": 3.423,
      "step": 430
    },
    {
      "epoch": 0.8576998050682261,
      "grad_norm": 5.590385437011719,
      "learning_rate": 3.57050032488629e-05,
      "loss": 3.6208,
      "step": 440
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 4.159304141998291,
      "learning_rate": 3.538011695906433e-05,
      "loss": 3.4107,
      "step": 450
    },
    {
      "epoch": 0.8966861598440545,
      "grad_norm": 5.699474334716797,
      "learning_rate": 3.505523066926576e-05,
      "loss": 3.3759,
      "step": 460
    },
    {
      "epoch": 0.9161793372319688,
      "grad_norm": 5.0284929275512695,
      "learning_rate": 3.473034437946719e-05,
      "loss": 3.4719,
      "step": 470
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 4.884040832519531,
      "learning_rate": 3.440545808966862e-05,
      "loss": 3.5534,
      "step": 480
    },
    {
      "epoch": 0.9551656920077972,
      "grad_norm": 5.428916931152344,
      "learning_rate": 3.4080571799870045e-05,
      "loss": 3.3919,
      "step": 490
    },
    {
      "epoch": 0.9746588693957114,
      "grad_norm": 5.549111843109131,
      "learning_rate": 3.3755685510071476e-05,
      "loss": 3.2799,
      "step": 500
    },
    {
      "epoch": 0.9941520467836257,
      "grad_norm": 5.919485092163086,
      "learning_rate": 3.3430799220272906e-05,
      "loss": 3.6097,
      "step": 510
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.2824156284332275,
      "eval_runtime": 21.5834,
      "eval_samples_per_second": 21.127,
      "eval_steps_per_second": 2.641,
      "step": 513
    },
    {
      "epoch": 1.01364522417154,
      "grad_norm": 4.9640631675720215,
      "learning_rate": 3.3105912930474336e-05,
      "loss": 3.2341,
      "step": 520
    },
    {
      "epoch": 1.0331384015594542,
      "grad_norm": 5.887562274932861,
      "learning_rate": 3.2781026640675766e-05,
      "loss": 3.0186,
      "step": 530
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 7.111718654632568,
      "learning_rate": 3.24561403508772e-05,
      "loss": 3.0381,
      "step": 540
    },
    {
      "epoch": 1.0721247563352827,
      "grad_norm": 6.662885665893555,
      "learning_rate": 3.213125406107863e-05,
      "loss": 3.0068,
      "step": 550
    },
    {
      "epoch": 1.0916179337231968,
      "grad_norm": 5.402489185333252,
      "learning_rate": 3.180636777128006e-05,
      "loss": 3.0492,
      "step": 560
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 6.615454196929932,
      "learning_rate": 3.148148148148148e-05,
      "loss": 2.9823,
      "step": 570
    },
    {
      "epoch": 1.1306042884990253,
      "grad_norm": 6.344214916229248,
      "learning_rate": 3.115659519168291e-05,
      "loss": 2.863,
      "step": 580
    },
    {
      "epoch": 1.1500974658869396,
      "grad_norm": 6.1259589195251465,
      "learning_rate": 3.083170890188434e-05,
      "loss": 2.9253,
      "step": 590
    },
    {
      "epoch": 1.1695906432748537,
      "grad_norm": 5.922159671783447,
      "learning_rate": 3.050682261208577e-05,
      "loss": 3.1142,
      "step": 600
    },
    {
      "epoch": 1.189083820662768,
      "grad_norm": 4.965208530426025,
      "learning_rate": 3.0181936322287202e-05,
      "loss": 3.0236,
      "step": 610
    },
    {
      "epoch": 1.2085769980506822,
      "grad_norm": 4.726465225219727,
      "learning_rate": 2.9857050032488632e-05,
      "loss": 3.114,
      "step": 620
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 5.802026748657227,
      "learning_rate": 2.9532163742690062e-05,
      "loss": 2.9944,
      "step": 630
    },
    {
      "epoch": 1.2475633528265107,
      "grad_norm": 5.344657897949219,
      "learning_rate": 2.920727745289149e-05,
      "loss": 3.024,
      "step": 640
    },
    {
      "epoch": 1.267056530214425,
      "grad_norm": 6.377889633178711,
      "learning_rate": 2.888239116309292e-05,
      "loss": 3.1357,
      "step": 650
    },
    {
      "epoch": 1.286549707602339,
      "grad_norm": 5.2032694816589355,
      "learning_rate": 2.855750487329435e-05,
      "loss": 3.0854,
      "step": 660
    },
    {
      "epoch": 1.3060428849902534,
      "grad_norm": 5.197242736816406,
      "learning_rate": 2.823261858349578e-05,
      "loss": 3.1208,
      "step": 670
    },
    {
      "epoch": 1.3255360623781676,
      "grad_norm": 5.073383808135986,
      "learning_rate": 2.7907732293697207e-05,
      "loss": 2.9982,
      "step": 680
    },
    {
      "epoch": 1.345029239766082,
      "grad_norm": 5.227969646453857,
      "learning_rate": 2.7582846003898637e-05,
      "loss": 3.0834,
      "step": 690
    },
    {
      "epoch": 1.364522417153996,
      "grad_norm": 5.831137657165527,
      "learning_rate": 2.7257959714100068e-05,
      "loss": 3.0019,
      "step": 700
    },
    {
      "epoch": 1.3840155945419104,
      "grad_norm": 5.306942939758301,
      "learning_rate": 2.6933073424301498e-05,
      "loss": 2.9489,
      "step": 710
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 5.346749305725098,
      "learning_rate": 2.6608187134502928e-05,
      "loss": 3.0281,
      "step": 720
    },
    {
      "epoch": 1.4230019493177388,
      "grad_norm": 4.3056817054748535,
      "learning_rate": 2.6283300844704355e-05,
      "loss": 2.8552,
      "step": 730
    },
    {
      "epoch": 1.442495126705653,
      "grad_norm": 8.335524559020996,
      "learning_rate": 2.5958414554905785e-05,
      "loss": 2.9833,
      "step": 740
    },
    {
      "epoch": 1.4619883040935673,
      "grad_norm": 4.510199069976807,
      "learning_rate": 2.5633528265107216e-05,
      "loss": 3.01,
      "step": 750
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 4.329857349395752,
      "learning_rate": 2.5308641975308646e-05,
      "loss": 3.0841,
      "step": 760
    },
    {
      "epoch": 1.5009746588693957,
      "grad_norm": 4.561777114868164,
      "learning_rate": 2.4983755685510073e-05,
      "loss": 2.9037,
      "step": 770
    },
    {
      "epoch": 1.52046783625731,
      "grad_norm": 4.895258903503418,
      "learning_rate": 2.46588693957115e-05,
      "loss": 2.9441,
      "step": 780
    },
    {
      "epoch": 1.5399610136452242,
      "grad_norm": 4.836617946624756,
      "learning_rate": 2.433398310591293e-05,
      "loss": 2.9684,
      "step": 790
    },
    {
      "epoch": 1.5594541910331383,
      "grad_norm": 5.523194789886475,
      "learning_rate": 2.400909681611436e-05,
      "loss": 3.0216,
      "step": 800
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 6.470391750335693,
      "learning_rate": 2.368421052631579e-05,
      "loss": 2.9688,
      "step": 810
    },
    {
      "epoch": 1.598440545808967,
      "grad_norm": 5.374258995056152,
      "learning_rate": 2.3359324236517217e-05,
      "loss": 2.934,
      "step": 820
    },
    {
      "epoch": 1.6179337231968811,
      "grad_norm": 4.702390670776367,
      "learning_rate": 2.3034437946718648e-05,
      "loss": 2.8229,
      "step": 830
    },
    {
      "epoch": 1.6374269005847952,
      "grad_norm": 4.931224822998047,
      "learning_rate": 2.2709551656920078e-05,
      "loss": 2.9748,
      "step": 840
    },
    {
      "epoch": 1.6569200779727096,
      "grad_norm": 5.478194713592529,
      "learning_rate": 2.2384665367121508e-05,
      "loss": 2.8791,
      "step": 850
    },
    {
      "epoch": 1.676413255360624,
      "grad_norm": 4.936557769775391,
      "learning_rate": 2.205977907732294e-05,
      "loss": 2.9022,
      "step": 860
    },
    {
      "epoch": 1.695906432748538,
      "grad_norm": 5.581218242645264,
      "learning_rate": 2.1734892787524365e-05,
      "loss": 3.0293,
      "step": 870
    },
    {
      "epoch": 1.7153996101364521,
      "grad_norm": 6.841440677642822,
      "learning_rate": 2.1410006497725796e-05,
      "loss": 2.9343,
      "step": 880
    },
    {
      "epoch": 1.7348927875243665,
      "grad_norm": 5.218410968780518,
      "learning_rate": 2.1085120207927226e-05,
      "loss": 3.0231,
      "step": 890
    },
    {
      "epoch": 1.7543859649122808,
      "grad_norm": 5.5271077156066895,
      "learning_rate": 2.0760233918128656e-05,
      "loss": 2.8563,
      "step": 900
    },
    {
      "epoch": 1.773879142300195,
      "grad_norm": 5.889744758605957,
      "learning_rate": 2.0435347628330083e-05,
      "loss": 3.0004,
      "step": 910
    },
    {
      "epoch": 1.793372319688109,
      "grad_norm": 5.243134498596191,
      "learning_rate": 2.0110461338531513e-05,
      "loss": 2.7516,
      "step": 920
    },
    {
      "epoch": 1.8128654970760234,
      "grad_norm": 5.98087739944458,
      "learning_rate": 1.9785575048732944e-05,
      "loss": 3.0529,
      "step": 930
    },
    {
      "epoch": 1.8323586744639377,
      "grad_norm": 4.677685737609863,
      "learning_rate": 1.9460688758934374e-05,
      "loss": 2.8891,
      "step": 940
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 6.311639308929443,
      "learning_rate": 1.91358024691358e-05,
      "loss": 2.9617,
      "step": 950
    },
    {
      "epoch": 1.871345029239766,
      "grad_norm": 4.64074182510376,
      "learning_rate": 1.881091617933723e-05,
      "loss": 2.9111,
      "step": 960
    },
    {
      "epoch": 1.8908382066276803,
      "grad_norm": 4.606050491333008,
      "learning_rate": 1.848602988953866e-05,
      "loss": 2.8621,
      "step": 970
    },
    {
      "epoch": 1.9103313840155947,
      "grad_norm": 4.810323238372803,
      "learning_rate": 1.816114359974009e-05,
      "loss": 3.017,
      "step": 980
    },
    {
      "epoch": 1.9298245614035088,
      "grad_norm": 5.766260147094727,
      "learning_rate": 1.7836257309941522e-05,
      "loss": 2.8715,
      "step": 990
    },
    {
      "epoch": 1.949317738791423,
      "grad_norm": 5.515121936798096,
      "learning_rate": 1.751137102014295e-05,
      "loss": 2.9338,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1539,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2089552379904000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}