{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09995147986414361,
  "eval_steps": 103,
  "global_step": 103,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009704027171276079,
      "grad_norm": 0.1630859375,
      "learning_rate": 2e-07,
      "loss": 2.2674,
      "step": 1
    },
    {
      "epoch": 0.0009704027171276079,
      "eval_loss": 2.3277485370635986,
      "eval_runtime": 707.6734,
      "eval_samples_per_second": 0.916,
      "eval_steps_per_second": 0.229,
      "step": 1
    },
    {
      "epoch": 0.0019408054342552159,
      "grad_norm": 0.1728515625,
      "learning_rate": 4e-07,
      "loss": 2.2913,
      "step": 2
    },
    {
      "epoch": 0.002911208151382824,
      "grad_norm": 0.169921875,
      "learning_rate": 6e-07,
      "loss": 2.2295,
      "step": 3
    },
    {
      "epoch": 0.0038816108685104317,
      "grad_norm": 0.1611328125,
      "learning_rate": 8e-07,
      "loss": 2.3423,
      "step": 4
    },
    {
      "epoch": 0.0048520135856380394,
      "grad_norm": 0.17578125,
      "learning_rate": 1e-06,
      "loss": 2.4168,
      "step": 5
    },
    {
      "epoch": 0.005822416302765648,
      "grad_norm": 0.17578125,
      "learning_rate": 1.2e-06,
      "loss": 2.1116,
      "step": 6
    },
    {
      "epoch": 0.006792819019893256,
      "grad_norm": 0.171875,
      "learning_rate": 1.4e-06,
      "loss": 2.3571,
      "step": 7
    },
    {
      "epoch": 0.0077632217370208634,
      "grad_norm": 0.1708984375,
      "learning_rate": 1.6e-06,
      "loss": 2.336,
      "step": 8
    },
    {
      "epoch": 0.008733624454148471,
      "grad_norm": 0.1474609375,
      "learning_rate": 1.8e-06,
      "loss": 2.2734,
      "step": 9
    },
    {
      "epoch": 0.009704027171276079,
      "grad_norm": 0.158203125,
      "learning_rate": 2e-06,
      "loss": 2.3191,
      "step": 10
    },
    {
      "epoch": 0.010674429888403688,
      "grad_norm": 0.140625,
      "learning_rate": 1.9999957311433394e-06,
      "loss": 2.1462,
      "step": 11
    },
    {
      "epoch": 0.011644832605531296,
      "grad_norm": 0.1455078125,
      "learning_rate": 1.999982924613854e-06,
      "loss": 2.3692,
      "step": 12
    },
    {
      "epoch": 0.012615235322658904,
      "grad_norm": 0.134765625,
      "learning_rate": 1.999961580533031e-06,
      "loss": 2.1327,
      "step": 13
    },
    {
      "epoch": 0.013585638039786511,
      "grad_norm": 0.130859375,
      "learning_rate": 1.9999316991033473e-06,
      "loss": 2.33,
      "step": 14
    },
    {
      "epoch": 0.01455604075691412,
      "grad_norm": 0.1357421875,
      "learning_rate": 1.999893280608269e-06,
      "loss": 2.1897,
      "step": 15
    },
    {
      "epoch": 0.015526443474041727,
      "grad_norm": 0.125,
      "learning_rate": 1.9998463254122472e-06,
      "loss": 2.3865,
      "step": 16
    },
    {
      "epoch": 0.016496846191169336,
      "grad_norm": 0.1240234375,
      "learning_rate": 1.9997908339607153e-06,
      "loss": 2.2324,
      "step": 17
    },
    {
      "epoch": 0.017467248908296942,
      "grad_norm": 0.12353515625,
      "learning_rate": 1.9997268067800845e-06,
      "loss": 2.3878,
      "step": 18
    },
    {
      "epoch": 0.018437651625424552,
      "grad_norm": 0.1396484375,
      "learning_rate": 1.9996542444777386e-06,
      "loss": 2.2695,
      "step": 19
    },
    {
      "epoch": 0.019408054342552158,
      "grad_norm": 0.1318359375,
      "learning_rate": 1.9995731477420292e-06,
      "loss": 2.2875,
      "step": 20
    },
    {
      "epoch": 0.020378457059679767,
      "grad_norm": 0.1357421875,
      "learning_rate": 1.999483517342268e-06,
      "loss": 2.4014,
      "step": 21
    },
    {
      "epoch": 0.021348859776807377,
      "grad_norm": 0.1376953125,
      "learning_rate": 1.9993853541287205e-06,
      "loss": 2.3639,
      "step": 22
    },
    {
      "epoch": 0.022319262493934983,
      "grad_norm": 0.1376953125,
      "learning_rate": 1.999278659032597e-06,
      "loss": 2.2434,
      "step": 23
    },
    {
      "epoch": 0.023289665211062592,
      "grad_norm": 0.1328125,
      "learning_rate": 1.9991634330660437e-06,
      "loss": 2.3897,
      "step": 24
    },
    {
      "epoch": 0.024260067928190198,
      "grad_norm": 0.126953125,
      "learning_rate": 1.999039677322135e-06,
      "loss": 2.2402,
      "step": 25
    },
    {
      "epoch": 0.025230470645317808,
      "grad_norm": 0.1279296875,
      "learning_rate": 1.998907392974861e-06,
      "loss": 2.401,
      "step": 26
    },
    {
      "epoch": 0.026200873362445413,
      "grad_norm": 0.12890625,
      "learning_rate": 1.9987665812791164e-06,
      "loss": 2.2646,
      "step": 27
    },
    {
      "epoch": 0.027171276079573023,
      "grad_norm": 0.12890625,
      "learning_rate": 1.9986172435706903e-06,
      "loss": 2.3168,
      "step": 28
    },
    {
      "epoch": 0.028141678796700632,
      "grad_norm": 0.1279296875,
      "learning_rate": 1.9984593812662525e-06,
      "loss": 2.3874,
      "step": 29
    },
    {
      "epoch": 0.02911208151382824,
      "grad_norm": 0.134765625,
      "learning_rate": 1.9982929958633397e-06,
      "loss": 2.3126,
      "step": 30
    },
    {
      "epoch": 0.030082484230955848,
      "grad_norm": 0.11376953125,
      "learning_rate": 1.998118088940341e-06,
      "loss": 2.233,
      "step": 31
    },
    {
      "epoch": 0.031052886948083454,
      "grad_norm": 0.125,
      "learning_rate": 1.9979346621564857e-06,
      "loss": 2.1122,
      "step": 32
    },
    {
      "epoch": 0.03202328966521106,
      "grad_norm": 0.1279296875,
      "learning_rate": 1.9977427172518227e-06,
      "loss": 2.2075,
      "step": 33
    },
    {
      "epoch": 0.03299369238233867,
      "grad_norm": 0.1259765625,
      "learning_rate": 1.9975422560472093e-06,
      "loss": 2.3974,
      "step": 34
    },
    {
      "epoch": 0.033964095099466275,
      "grad_norm": 0.1181640625,
      "learning_rate": 1.9973332804442895e-06,
      "loss": 2.344,
      "step": 35
    },
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 0.11962890625,
      "learning_rate": 1.997115792425479e-06,
      "loss": 2.2733,
      "step": 36
    },
    {
      "epoch": 0.035904900533721494,
      "grad_norm": 0.1318359375,
      "learning_rate": 1.996889794053945e-06,
      "loss": 2.2443,
      "step": 37
    },
    {
      "epoch": 0.036875303250849104,
      "grad_norm": 0.1220703125,
      "learning_rate": 1.9966552874735863e-06,
      "loss": 2.3253,
      "step": 38
    },
    {
      "epoch": 0.03784570596797671,
      "grad_norm": 0.1201171875,
      "learning_rate": 1.9964122749090145e-06,
      "loss": 2.393,
      "step": 39
    },
    {
      "epoch": 0.038816108685104316,
      "grad_norm": 0.1142578125,
      "learning_rate": 1.996160758665531e-06,
      "loss": 2.234,
      "step": 40
    },
    {
      "epoch": 0.039786511402231925,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.9959007411291063e-06,
      "loss": 2.1832,
      "step": 41
    },
    {
      "epoch": 0.040756914119359534,
      "grad_norm": 0.11962890625,
      "learning_rate": 1.995632224766358e-06,
      "loss": 2.2993,
      "step": 42
    },
    {
      "epoch": 0.041727316836487144,
      "grad_norm": 0.12060546875,
      "learning_rate": 1.995355212124525e-06,
      "loss": 2.4293,
      "step": 43
    },
    {
      "epoch": 0.04269771955361475,
      "grad_norm": 0.115234375,
      "learning_rate": 1.9950697058314457e-06,
      "loss": 2.1791,
      "step": 44
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 0.11328125,
      "learning_rate": 1.994775708595533e-06,
      "loss": 2.402,
      "step": 45
    },
    {
      "epoch": 0.044638524987869965,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.9944732232057465e-06,
      "loss": 2.271,
      "step": 46
    },
    {
      "epoch": 0.045608927704997575,
      "grad_norm": 0.10888671875,
      "learning_rate": 1.994162252531567e-06,
      "loss": 2.1897,
      "step": 47
    },
    {
      "epoch": 0.046579330422125184,
      "grad_norm": 0.11279296875,
      "learning_rate": 1.9938427995229723e-06,
      "loss": 2.268,
      "step": 48
    },
    {
      "epoch": 0.04754973313925279,
      "grad_norm": 0.125,
      "learning_rate": 1.993514867210404e-06,
      "loss": 2.2919,
      "step": 49
    },
    {
      "epoch": 0.048520135856380396,
      "grad_norm": 0.126953125,
      "learning_rate": 1.9931784587047422e-06,
      "loss": 2.4426,
      "step": 50
    },
    {
      "epoch": 0.049490538573508006,
      "grad_norm": 0.11767578125,
      "learning_rate": 1.9928335771972748e-06,
      "loss": 2.3823,
      "step": 51
    },
    {
      "epoch": 0.050460941290635615,
      "grad_norm": 0.11572265625,
      "learning_rate": 1.9924802259596686e-06,
      "loss": 2.2299,
      "step": 52
    },
    {
      "epoch": 0.051431344007763224,
      "grad_norm": 0.11767578125,
      "learning_rate": 1.9921184083439354e-06,
      "loss": 2.4699,
      "step": 53
    },
    {
      "epoch": 0.05240174672489083,
      "grad_norm": 0.11083984375,
      "learning_rate": 1.991748127782404e-06,
      "loss": 2.2251,
      "step": 54
    },
    {
      "epoch": 0.053372149442018436,
      "grad_norm": 0.1142578125,
      "learning_rate": 1.9913693877876844e-06,
      "loss": 2.204,
      "step": 55
    },
    {
      "epoch": 0.054342552159146046,
      "grad_norm": 0.111328125,
      "learning_rate": 1.9909821919526363e-06,
      "loss": 2.228,
      "step": 56
    },
    {
      "epoch": 0.055312954876273655,
      "grad_norm": 0.109375,
      "learning_rate": 1.9905865439503337e-06,
      "loss": 2.2021,
      "step": 57
    },
    {
      "epoch": 0.056283357593401265,
      "grad_norm": 0.10888671875,
      "learning_rate": 1.9901824475340314e-06,
      "loss": 2.2048,
      "step": 58
    },
    {
      "epoch": 0.05725376031052887,
      "grad_norm": 0.11279296875,
      "learning_rate": 1.9897699065371285e-06,
      "loss": 2.2993,
      "step": 59
    },
    {
      "epoch": 0.05822416302765648,
      "grad_norm": 0.111328125,
      "learning_rate": 1.9893489248731336e-06,
      "loss": 2.2354,
      "step": 60
    },
    {
      "epoch": 0.059194565744784086,
      "grad_norm": 0.123046875,
      "learning_rate": 1.9889195065356238e-06,
      "loss": 2.3262,
      "step": 61
    },
    {
      "epoch": 0.060164968461911696,
      "grad_norm": 0.11767578125,
      "learning_rate": 1.988481655598212e-06,
      "loss": 2.4042,
      "step": 62
    },
    {
      "epoch": 0.0611353711790393,
      "grad_norm": 0.1171875,
      "learning_rate": 1.988035376214504e-06,
      "loss": 2.2258,
      "step": 63
    },
    {
      "epoch": 0.06210577389616691,
      "grad_norm": 0.11669921875,
      "learning_rate": 1.987580672618062e-06,
      "loss": 2.2404,
      "step": 64
    },
    {
      "epoch": 0.06307617661329452,
      "grad_norm": 0.1142578125,
      "learning_rate": 1.987117549122363e-06,
      "loss": 2.398,
      "step": 65
    },
    {
      "epoch": 0.06404657933042213,
      "grad_norm": 0.1181640625,
      "learning_rate": 1.986646010120756e-06,
      "loss": 2.264,
      "step": 66
    },
    {
      "epoch": 0.06501698204754973,
      "grad_norm": 0.1162109375,
      "learning_rate": 1.986166060086425e-06,
      "loss": 2.3085,
      "step": 67
    },
    {
      "epoch": 0.06598738476467735,
      "grad_norm": 0.11669921875,
      "learning_rate": 1.985677703572344e-06,
      "loss": 2.219,
      "step": 68
    },
    {
      "epoch": 0.06695778748180495,
      "grad_norm": 0.1181640625,
      "learning_rate": 1.9851809452112317e-06,
      "loss": 2.2302,
      "step": 69
    },
    {
      "epoch": 0.06792819019893255,
      "grad_norm": 0.1142578125,
      "learning_rate": 1.9846757897155116e-06,
      "loss": 2.3431,
      "step": 70
    },
    {
      "epoch": 0.06889859291606017,
      "grad_norm": 0.11669921875,
      "learning_rate": 1.984162241877264e-06,
      "loss": 2.2894,
      "step": 71
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 0.11083984375,
      "learning_rate": 1.983640306568183e-06,
      "loss": 2.3387,
      "step": 72
    },
    {
      "epoch": 0.07083939835031539,
      "grad_norm": 0.11669921875,
      "learning_rate": 1.9831099887395287e-06,
      "loss": 2.092,
      "step": 73
    },
    {
      "epoch": 0.07180980106744299,
      "grad_norm": 0.123046875,
      "learning_rate": 1.98257129342208e-06,
      "loss": 2.3139,
      "step": 74
    },
    {
      "epoch": 0.07278020378457059,
      "grad_norm": 0.12158203125,
      "learning_rate": 1.9820242257260884e-06,
      "loss": 2.3842,
      "step": 75
    },
    {
      "epoch": 0.07375060650169821,
      "grad_norm": 0.111328125,
      "learning_rate": 1.981468790841229e-06,
      "loss": 2.2733,
      "step": 76
    },
    {
      "epoch": 0.07472100921882581,
      "grad_norm": 0.1044921875,
      "learning_rate": 1.9809049940365504e-06,
      "loss": 2.1439,
      "step": 77
    },
    {
      "epoch": 0.07569141193595343,
      "grad_norm": 0.10888671875,
      "learning_rate": 1.980332840660425e-06,
      "loss": 2.316,
      "step": 78
    },
    {
      "epoch": 0.07666181465308103,
      "grad_norm": 0.12255859375,
      "learning_rate": 1.979752336140499e-06,
      "loss": 2.4238,
      "step": 79
    },
    {
      "epoch": 0.07763221737020863,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.9791634859836408e-06,
      "loss": 2.2081,
      "step": 80
    },
    {
      "epoch": 0.07860262008733625,
      "grad_norm": 0.11572265625,
      "learning_rate": 1.978566295775887e-06,
      "loss": 2.3303,
      "step": 81
    },
    {
      "epoch": 0.07957302280446385,
      "grad_norm": 0.111328125,
      "learning_rate": 1.977960771182393e-06,
      "loss": 2.3657,
      "step": 82
    },
    {
      "epoch": 0.08054342552159147,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.9773469179473754e-06,
      "loss": 2.3921,
      "step": 83
    },
    {
      "epoch": 0.08151382823871907,
      "grad_norm": 0.1123046875,
      "learning_rate": 1.9767247418940593e-06,
      "loss": 2.3947,
      "step": 84
    },
    {
      "epoch": 0.08248423095584667,
      "grad_norm": 0.12109375,
      "learning_rate": 1.9760942489246236e-06,
      "loss": 2.2361,
      "step": 85
    },
    {
      "epoch": 0.08345463367297429,
      "grad_norm": 0.1083984375,
      "learning_rate": 1.975455445020144e-06,
      "loss": 2.1025,
      "step": 86
    },
    {
      "epoch": 0.08442503639010189,
      "grad_norm": 0.115234375,
      "learning_rate": 1.9748083362405373e-06,
      "loss": 2.4577,
      "step": 87
    },
    {
      "epoch": 0.0853954391072295,
      "grad_norm": 0.1171875,
      "learning_rate": 1.974152928724502e-06,
      "loss": 2.3706,
      "step": 88
    },
    {
      "epoch": 0.08636584182435711,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.973489228689463e-06,
      "loss": 2.4223,
      "step": 89
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.12158203125,
      "learning_rate": 1.9728172424315087e-06,
      "loss": 2.1975,
      "step": 90
    },
    {
      "epoch": 0.08830664725861233,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.9721369763253348e-06,
      "loss": 2.3638,
      "step": 91
    },
    {
      "epoch": 0.08927704997573993,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.9714484368241828e-06,
      "loss": 2.278,
      "step": 92
    },
    {
      "epoch": 0.09024745269286755,
      "grad_norm": 0.1123046875,
      "learning_rate": 1.9707516304597783e-06,
      "loss": 2.3421,
      "step": 93
    },
    {
      "epoch": 0.09121785540999515,
      "grad_norm": 0.1171875,
      "learning_rate": 1.9700465638422686e-06,
      "loss": 2.3418,
      "step": 94
    },
    {
      "epoch": 0.09218825812712275,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.9693332436601613e-06,
      "loss": 2.1814,
      "step": 95
    },
    {
      "epoch": 0.09315866084425037,
      "grad_norm": 0.1259765625,
      "learning_rate": 1.96861167668026e-06,
      "loss": 2.299,
      "step": 96
    },
    {
      "epoch": 0.09412906356137797,
      "grad_norm": 0.10791015625,
      "learning_rate": 1.9678818697476e-06,
      "loss": 2.1708,
      "step": 97
    },
    {
      "epoch": 0.09509946627850557,
      "grad_norm": 0.1171875,
      "learning_rate": 1.9671438297853845e-06,
      "loss": 2.3062,
      "step": 98
    },
    {
      "epoch": 0.09606986899563319,
      "grad_norm": 0.11669921875,
      "learning_rate": 1.9663975637949172e-06,
      "loss": 2.2044,
      "step": 99
    },
    {
      "epoch": 0.09704027171276079,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.9656430788555372e-06,
      "loss": 2.1654,
      "step": 100
    },
    {
      "epoch": 0.09801067442988841,
      "grad_norm": 0.1279296875,
      "learning_rate": 1.964880382124551e-06,
      "loss": 2.3448,
      "step": 101
    },
    {
      "epoch": 0.09898107714701601,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.964109480837165e-06,
      "loss": 2.2951,
      "step": 102
    },
    {
      "epoch": 0.09995147986414361,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.9633303823064186e-06,
      "loss": 2.2252,
      "step": 103
    },
    {
      "epoch": 0.09995147986414361,
      "eval_loss": 2.3053860664367676,
      "eval_runtime": 714.5363,
      "eval_samples_per_second": 0.907,
      "eval_steps_per_second": 0.227,
      "step": 103
    }
  ],
  "logging_steps": 1,
  "max_steps": 1030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 103,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1285759393293926e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}