{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.935672514619883,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 2.949489116668701,
      "learning_rate": 0.0002,
      "loss": 6.8731,
      "step": 1
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.4809715747833252,
      "learning_rate": 0.0002,
      "loss": 5.7442,
      "step": 2
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.701913595199585,
      "learning_rate": 0.0002,
      "loss": 5.3638,
      "step": 3
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.2592666149139404,
      "learning_rate": 0.0002,
      "loss": 4.7664,
      "step": 4
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.6057344675064087,
      "learning_rate": 0.0002,
      "loss": 4.7581,
      "step": 5
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.9201135635375977,
      "learning_rate": 0.0002,
      "loss": 4.5088,
      "step": 6
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.3088886737823486,
      "learning_rate": 0.0002,
      "loss": 4.1351,
      "step": 7
    },
    {
      "epoch": 0.07,
      "grad_norm": 3.622396945953369,
      "learning_rate": 0.0002,
      "loss": 4.5207,
      "step": 8
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.80634880065918,
      "learning_rate": 0.0002,
      "loss": 4.1157,
      "step": 9
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.79710578918457,
      "learning_rate": 0.0002,
      "loss": 3.3101,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 7.330948352813721,
      "learning_rate": 0.0002,
      "loss": 3.4536,
      "step": 11
    },
    {
      "epoch": 0.11,
      "grad_norm": 6.117642879486084,
      "learning_rate": 0.0002,
      "loss": 3.1297,
      "step": 12
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.200116157531738,
      "learning_rate": 0.0002,
      "loss": 2.5508,
      "step": 13
    },
    {
      "epoch": 0.13,
      "grad_norm": 3.4331789016723633,
      "learning_rate": 0.0002,
      "loss": 2.2032,
      "step": 14
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.8927509784698486,
      "learning_rate": 0.0002,
      "loss": 2.1005,
      "step": 15
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.9786716103553772,
      "learning_rate": 0.0002,
      "loss": 2.1406,
      "step": 16
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8695776462554932,
      "learning_rate": 0.0002,
      "loss": 1.9371,
      "step": 17
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8738767504692078,
      "learning_rate": 0.0002,
      "loss": 1.9745,
      "step": 18
    },
    {
      "epoch": 0.18,
      "grad_norm": 7.5855231285095215,
      "learning_rate": 0.0002,
      "loss": 2.0879,
      "step": 19
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.1819020509719849,
      "learning_rate": 0.0002,
      "loss": 1.903,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0826493501663208,
      "learning_rate": 0.0002,
      "loss": 1.9642,
      "step": 21
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.9060399532318115,
      "learning_rate": 0.0002,
      "loss": 1.9963,
      "step": 22
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.7423937916755676,
      "learning_rate": 0.0002,
      "loss": 1.9192,
      "step": 23
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.6615855097770691,
      "learning_rate": 0.0002,
      "loss": 1.8811,
      "step": 24
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.700908362865448,
      "learning_rate": 0.0002,
      "loss": 1.8524,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5277789831161499,
      "learning_rate": 0.0002,
      "loss": 1.8696,
      "step": 26
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.42331141233444214,
      "learning_rate": 0.0002,
      "loss": 1.7229,
      "step": 27
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.42249181866645813,
      "learning_rate": 0.0002,
      "loss": 1.7733,
      "step": 28
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4419895112514496,
      "learning_rate": 0.0002,
      "loss": 1.7343,
      "step": 29
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5018438100814819,
      "learning_rate": 0.0002,
      "loss": 1.6586,
      "step": 30
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5385031700134277,
      "learning_rate": 0.0002,
      "loss": 1.7018,
      "step": 31
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.4651014506816864,
      "learning_rate": 0.0002,
      "loss": 1.7329,
      "step": 32
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.6264488101005554,
      "learning_rate": 0.0002,
      "loss": 1.5911,
      "step": 33
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.46918559074401855,
      "learning_rate": 0.0002,
      "loss": 1.6609,
      "step": 34
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6417805552482605,
      "learning_rate": 0.0002,
      "loss": 1.6976,
      "step": 35
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.5029424428939819,
      "learning_rate": 0.0002,
      "loss": 1.7227,
      "step": 36
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6494549512863159,
      "learning_rate": 0.0002,
      "loss": 1.6332,
      "step": 37
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5361642241477966,
      "learning_rate": 0.0002,
      "loss": 1.6417,
      "step": 38
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8852269649505615,
      "learning_rate": 0.0002,
      "loss": 1.7352,
      "step": 39
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.72622150182724,
      "learning_rate": 0.0002,
      "loss": 1.6965,
      "step": 40
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.578904390335083,
      "learning_rate": 0.0002,
      "loss": 1.7407,
      "step": 41
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5193885564804077,
      "learning_rate": 0.0002,
      "loss": 1.6437,
      "step": 42
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5035353302955627,
      "learning_rate": 0.0002,
      "loss": 1.5735,
      "step": 43
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8882142305374146,
      "learning_rate": 0.0002,
      "loss": 1.7808,
      "step": 44
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.5434024333953857,
      "learning_rate": 0.0002,
      "loss": 1.638,
      "step": 45
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.7970778346061707,
      "learning_rate": 0.0002,
      "loss": 1.621,
      "step": 46
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5033506751060486,
      "learning_rate": 0.0002,
      "loss": 1.6199,
      "step": 47
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.8881465196609497,
      "learning_rate": 0.0002,
      "loss": 1.7907,
      "step": 48
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.741858184337616,
      "learning_rate": 0.0002,
      "loss": 1.6585,
      "step": 49
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.8896893858909607,
      "learning_rate": 0.0002,
      "loss": 1.7583,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6767799854278564,
      "learning_rate": 0.0002,
      "loss": 1.6116,
      "step": 51
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6831919550895691,
      "learning_rate": 0.0002,
      "loss": 1.5806,
      "step": 52
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6259914040565491,
      "learning_rate": 0.0002,
      "loss": 1.6619,
      "step": 53
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.9376181960105896,
      "learning_rate": 0.0002,
      "loss": 1.6375,
      "step": 54
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.7372838854789734,
      "learning_rate": 0.0002,
      "loss": 1.5599,
      "step": 55
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5478132367134094,
      "learning_rate": 0.0002,
      "loss": 1.6093,
      "step": 56
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.9254269599914551,
      "learning_rate": 0.0002,
      "loss": 1.7051,
      "step": 57
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.7650561332702637,
      "learning_rate": 0.0002,
      "loss": 1.6095,
      "step": 58
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.612433135509491,
      "learning_rate": 0.0002,
      "loss": 1.5595,
      "step": 59
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.4704805314540863,
      "learning_rate": 0.0002,
      "loss": 1.6785,
      "step": 60
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.705121636390686,
      "learning_rate": 0.0002,
      "loss": 1.6318,
      "step": 61
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.7150620222091675,
      "learning_rate": 0.0002,
      "loss": 1.5746,
      "step": 62
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5674924254417419,
      "learning_rate": 0.0002,
      "loss": 1.5223,
      "step": 63
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5296141505241394,
      "learning_rate": 0.0002,
      "loss": 1.5045,
      "step": 64
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.43603238463401794,
      "learning_rate": 0.0002,
      "loss": 1.6686,
      "step": 65
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.3482309877872467,
      "learning_rate": 0.0002,
      "loss": 1.6189,
      "step": 66
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.4482012987136841,
      "learning_rate": 0.0002,
      "loss": 1.6339,
      "step": 67
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.47700467705726624,
      "learning_rate": 0.0002,
      "loss": 1.5819,
      "step": 68
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5465943813323975,
      "learning_rate": 0.0002,
      "loss": 1.5073,
      "step": 69
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.41377145051956177,
      "learning_rate": 0.0002,
      "loss": 1.5552,
      "step": 70
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.5941596031188965,
      "learning_rate": 0.0002,
      "loss": 1.505,
      "step": 71
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.6071710586547852,
      "learning_rate": 0.0002,
      "loss": 1.558,
      "step": 72
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5148259401321411,
      "learning_rate": 0.0002,
      "loss": 1.4633,
      "step": 73
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.30810546875,
      "learning_rate": 0.0002,
      "loss": 1.4482,
      "step": 74
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4432346820831299,
      "learning_rate": 0.0002,
      "loss": 1.5734,
      "step": 75
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.689092218875885,
      "learning_rate": 0.0002,
      "loss": 1.5621,
      "step": 76
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6650224328041077,
      "learning_rate": 0.0002,
      "loss": 1.5063,
      "step": 77
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.728783905506134,
      "learning_rate": 0.0002,
      "loss": 1.518,
      "step": 78
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.7941334247589111,
      "learning_rate": 0.0002,
      "loss": 1.5284,
      "step": 79
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.8526914119720459,
      "learning_rate": 0.0002,
      "loss": 1.4954,
      "step": 80
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.9384956359863281,
      "learning_rate": 0.0002,
      "loss": 1.5753,
      "step": 81
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5513901114463806,
      "learning_rate": 0.0002,
      "loss": 1.5513,
      "step": 82
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.7507538795471191,
      "learning_rate": 0.0002,
      "loss": 1.5172,
      "step": 83
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.40390703082084656,
      "learning_rate": 0.0002,
      "loss": 1.5035,
      "step": 84
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8725360631942749,
      "learning_rate": 0.0002,
      "loss": 1.6118,
      "step": 85
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4920073449611664,
      "learning_rate": 0.0002,
      "loss": 1.5111,
      "step": 86
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5495926737785339,
      "learning_rate": 0.0002,
      "loss": 1.5781,
      "step": 87
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.5326025485992432,
      "learning_rate": 0.0002,
      "loss": 1.6479,
      "step": 88
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.3922731578350067,
      "learning_rate": 0.0002,
      "loss": 1.6432,
      "step": 89
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0725717544555664,
      "learning_rate": 0.0002,
      "loss": 1.6326,
      "step": 90
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.849716305732727,
      "learning_rate": 0.0002,
      "loss": 1.5013,
      "step": 91
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.3658522963523865,
      "learning_rate": 0.0002,
      "loss": 1.5405,
      "step": 92
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.7757679224014282,
      "learning_rate": 0.0002,
      "loss": 1.5823,
      "step": 93
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5468668341636658,
      "learning_rate": 0.0002,
      "loss": 1.5345,
      "step": 94
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.28030768036842346,
      "learning_rate": 0.0002,
      "loss": 1.4525,
      "step": 95
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.636431097984314,
      "learning_rate": 0.0002,
      "loss": 1.5195,
      "step": 96
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5017719268798828,
      "learning_rate": 0.0002,
      "loss": 1.4132,
      "step": 97
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.443892240524292,
      "learning_rate": 0.0002,
      "loss": 1.506,
      "step": 98
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.575356125831604,
      "learning_rate": 0.0002,
      "loss": 1.5295,
      "step": 99
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4003719687461853,
      "learning_rate": 0.0002,
      "loss": 1.491,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 106,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 1.563282263506944e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}