{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 2.2997210025787354,
      "learning_rate": 0.00015998457923856519,
      "loss": 1.2401,
      "step": 1
    },
    {
      "epoch": 0.025,
      "grad_norm": 24.28518295288086,
      "learning_rate": 0.00015993832289925785,
      "loss": 4.0648,
      "step": 2
    },
    {
      "epoch": 0.0375,
      "grad_norm": 12.727800369262695,
      "learning_rate": 0.0001598612488147773,
      "loss": 2.7044,
      "step": 3
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.934032440185547,
      "learning_rate": 0.00015975338669865026,
      "loss": 1.994,
      "step": 4
    },
    {
      "epoch": 0.0625,
      "grad_norm": 8.1886625289917,
      "learning_rate": 0.00015961477813377576,
      "loss": 2.1426,
      "step": 5
    },
    {
      "epoch": 0.075,
      "grad_norm": 2.910872220993042,
      "learning_rate": 0.00015944547655639412,
      "loss": 1.7254,
      "step": 6
    },
    {
      "epoch": 0.0875,
      "grad_norm": 1.565290093421936,
      "learning_rate": 0.00015924554723548617,
      "loss": 1.5187,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.9080827236175537,
      "learning_rate": 0.00015901506724761103,
      "loss": 1.5405,
      "step": 8
    },
    {
      "epoch": 0.1125,
      "grad_norm": 1.875126838684082,
      "learning_rate": 0.00015875412544719134,
      "loss": 1.4493,
      "step": 9
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.2589935064315796,
      "learning_rate": 0.00015846282243225845,
      "loss": 1.4103,
      "step": 10
    },
    {
      "epoch": 0.1375,
      "grad_norm": 1.2925529479980469,
      "learning_rate": 0.0001581412705056698,
      "loss": 1.3507,
      "step": 11
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.4467802047729492,
      "learning_rate": 0.00015778959363181415,
      "loss": 1.3,
      "step": 12
    },
    {
      "epoch": 0.1625,
      "grad_norm": 1.267639398574829,
      "learning_rate": 0.0001574079273888208,
      "loss": 1.2974,
      "step": 13
    },
    {
      "epoch": 0.175,
      "grad_norm": 1.0911085605621338,
      "learning_rate": 0.00015699641891629178,
      "loss": 1.2635,
      "step": 14
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.9065354466438293,
      "learning_rate": 0.00015655522685857672,
      "loss": 1.2119,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7415559887886047,
      "learning_rate": 0.0001560845213036123,
      "loss": 1.2337,
      "step": 16
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.7553166151046753,
      "learning_rate": 0.00015558448371735025,
      "loss": 1.1884,
      "step": 17
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.5407947301864624,
      "learning_rate": 0.00015505530687379875,
      "loss": 1.17,
      "step": 18
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.5162355899810791,
      "learning_rate": 0.00015449719478070428,
      "loss": 1.1879,
      "step": 19
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5688554644584656,
      "learning_rate": 0.00015391036260090294,
      "loss": 1.1767,
      "step": 20
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.48555564880371094,
      "learning_rate": 0.0001532950365693709,
      "loss": 1.1726,
      "step": 21
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.4502723515033722,
      "learning_rate": 0.00015265145390600652,
      "loss": 1.163,
      "step": 22
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.3590157926082611,
      "learning_rate": 0.00015197986272417774,
      "loss": 1.1839,
      "step": 23
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.38364410400390625,
      "learning_rate": 0.00015128052193506944,
      "loss": 1.1642,
      "step": 24
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.36856546998023987,
      "learning_rate": 0.0001505537011478684,
      "loss": 1.1495,
      "step": 25
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.3514528274536133,
      "learning_rate": 0.0001497996805658238,
      "loss": 1.1257,
      "step": 26
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.42414528131484985,
      "learning_rate": 0.00014901875087822337,
      "loss": 1.1463,
      "step": 27
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.35511669516563416,
      "learning_rate": 0.0001482112131483274,
      "loss": 1.141,
      "step": 28
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.3799460530281067,
      "learning_rate": 0.00014737737869730292,
      "loss": 1.1414,
      "step": 29
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.26333189010620117,
      "learning_rate": 0.00014651756898420365,
      "loss": 1.1352,
      "step": 30
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.37996864318847656,
      "learning_rate": 0.0001456321154820411,
      "loss": 1.1167,
      "step": 31
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.3210310637950897,
      "learning_rate": 0.00014472135954999581,
      "loss": 1.113,
      "step": 32
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.342960923910141,
      "learning_rate": 0.00014378565230181657,
      "loss": 1.1201,
      "step": 33
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.30171331763267517,
      "learning_rate": 0.0001428253544704596,
      "loss": 1.1303,
      "step": 34
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.3308579623699188,
      "learning_rate": 0.00014184083626901897,
      "loss": 1.135,
      "step": 35
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.33749139308929443,
      "learning_rate": 0.0001408324772480025,
      "loss": 1.1413,
      "step": 36
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.29873886704444885,
      "learning_rate": 0.00013980066614900776,
      "loss": 1.1406,
      "step": 37
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.25276514887809753,
      "learning_rate": 0.00013874580075485485,
      "loss": 1.1421,
      "step": 38
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.2849913537502289,
      "learning_rate": 0.00013766828773623352,
      "loss": 1.1298,
      "step": 39
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.27665936946868896,
      "learning_rate": 0.00013656854249492382,
      "loss": 1.1052,
      "step": 40
    },
    {
      "epoch": 0.5125,
      "grad_norm": 0.31618547439575195,
      "learning_rate": 0.0001354469890036509,
      "loss": 1.1124,
      "step": 41
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.30855098366737366,
      "learning_rate": 0.00013430405964263536,
      "loss": 1.1164,
      "step": 42
    },
    {
      "epoch": 0.5375,
      "grad_norm": 0.24974325299263,
      "learning_rate": 0.00013314019503290255,
      "loss": 1.1379,
      "step": 43
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.259245365858078,
      "learning_rate": 0.00013195584386641469,
      "loss": 1.0963,
      "step": 44
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.3342917561531067,
      "learning_rate": 0.00013075146273309164,
      "loss": 1.1089,
      "step": 45
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.3317720293998718,
      "learning_rate": 0.00012952751594478675,
      "loss": 1.1226,
      "step": 46
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.2566727101802826,
      "learning_rate": 0.0001282844753562857,
      "loss": 1.1035,
      "step": 47
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.25012263655662537,
      "learning_rate": 0.00012702282018339786,
      "loss": 1.0713,
      "step": 48
    },
    {
      "epoch": 0.6125,
      "grad_norm": 0.2855740189552307,
      "learning_rate": 0.00012574303681820898,
      "loss": 1.1232,
      "step": 49
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.21377117931842804,
      "learning_rate": 0.0001244456186415682,
      "loss": 1.0726,
      "step": 50
    },
    {
      "epoch": 0.6375,
      "grad_norm": 0.3012278079986572,
      "learning_rate": 0.00012313106583288004,
      "loss": 1.0855,
      "step": 51
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2754627764225006,
      "learning_rate": 0.00012179988517727591,
      "loss": 1.113,
      "step": 52
    },
    {
      "epoch": 0.6625,
      "grad_norm": 0.2773728668689728,
      "learning_rate": 0.00012045258987023879,
      "loss": 1.0931,
      "step": 53
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.3616091012954712,
      "learning_rate": 0.00011908969931975641,
      "loss": 1.1007,
      "step": 54
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.28011709451675415,
      "learning_rate": 0.00011771173894607985,
      "loss": 1.1312,
      "step": 55
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.19245974719524384,
      "learning_rate": 0.00011631923997916375,
      "loss": 1.0784,
      "step": 56
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.2807864844799042,
      "learning_rate": 0.00011491273925386736,
      "loss": 1.0766,
      "step": 57
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.25869062542915344,
      "learning_rate": 0.00011349277900299426,
      "loss": 1.0929,
      "step": 58
    },
    {
      "epoch": 0.7375,
      "grad_norm": 0.20374780893325806,
      "learning_rate": 0.00011205990664825127,
      "loss": 1.0977,
      "step": 59
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.275302529335022,
      "learning_rate": 0.00011061467458920719,
      "loss": 1.1218,
      "step": 60
    },
    {
      "epoch": 0.7625,
      "grad_norm": 0.26479312777519226,
      "learning_rate": 0.00010915763999033201,
      "loss": 1.0972,
      "step": 61
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.20327049493789673,
      "learning_rate": 0.00010768936456619945,
      "loss": 1.0723,
      "step": 62
    },
    {
      "epoch": 0.7875,
      "grad_norm": 0.18908362090587616,
      "learning_rate": 0.0001062104143649355,
      "loss": 1.1059,
      "step": 63
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2153932750225067,
      "learning_rate": 0.0001047213595499958,
      "loss": 1.1112,
      "step": 64
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.23449215292930603,
      "learning_rate": 0.000103222774180357,
      "loss": 1.1125,
      "step": 65
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.19739866256713867,
      "learning_rate": 0.00010171523598920594,
      "loss": 1.0506,
      "step": 66
    },
    {
      "epoch": 0.8375,
      "grad_norm": 0.579247236251831,
      "learning_rate": 0.00010019932616121264,
      "loss": 1.0599,
      "step": 67
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2158878892660141,
      "learning_rate": 9.867562910847246e-05,
      "loss": 1.1116,
      "step": 68
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.24534355103969574,
      "learning_rate": 9.714473224520406e-05,
      "loss": 1.1039,
      "step": 69
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.1604059487581253,
      "learning_rate": 9.560722576129029e-05,
      "loss": 1.1007,
      "step": 70
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.24135896563529968,
      "learning_rate": 9.406370239474839e-05,
      "loss": 1.0976,
      "step": 71
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.2200448215007782,
      "learning_rate": 9.251475720321848e-05,
      "loss": 1.1001,
      "step": 72
    },
    {
      "epoch": 0.9125,
      "grad_norm": 0.17517372965812683,
      "learning_rate": 9.096098733455746e-05,
      "loss": 1.0864,
      "step": 73
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.23631267249584198,
      "learning_rate": 8.940299179662703e-05,
      "loss": 1.0976,
      "step": 74
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.17627741396427155,
      "learning_rate": 8.784137122636488e-05,
      "loss": 1.1049,
      "step": 75
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.1840021312236786,
      "learning_rate": 8.627672765822762e-05,
      "loss": 1.0504,
      "step": 76
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.1925836205482483,
      "learning_rate": 8.470966429209512e-05,
      "loss": 1.1028,
      "step": 77
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.18122681975364685,
      "learning_rate": 8.31407852607255e-05,
      "loss": 1.0605,
      "step": 78
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.16970321536064148,
      "learning_rate": 8.157069539685026e-05,
      "loss": 1.1069,
      "step": 79
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2044173628091812,
      "learning_rate": 8e-05,
      "loss": 1.1173,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6380640896784794e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}