{
  "best_metric": 1.2729405164718628,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.5194805194805194,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005194805194805195,
      "grad_norm": 0.4177940785884857,
      "learning_rate": 1e-05,
      "loss": 1.3458,
      "step": 1
    },
    {
      "epoch": 0.005194805194805195,
      "eval_loss": 1.5109460353851318,
      "eval_runtime": 31.5573,
      "eval_samples_per_second": 5.165,
      "eval_steps_per_second": 1.299,
      "step": 1
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 0.40045127272605896,
      "learning_rate": 2e-05,
      "loss": 1.4257,
      "step": 2
    },
    {
      "epoch": 0.015584415584415584,
      "grad_norm": 0.3874695301055908,
      "learning_rate": 3e-05,
      "loss": 1.4884,
      "step": 3
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 0.34974992275238037,
      "learning_rate": 4e-05,
      "loss": 1.361,
      "step": 4
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 0.35995498299598694,
      "learning_rate": 5e-05,
      "loss": 1.2804,
      "step": 5
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 0.3070196807384491,
      "learning_rate": 6e-05,
      "loss": 1.305,
      "step": 6
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.3768017292022705,
      "learning_rate": 7e-05,
      "loss": 1.3585,
      "step": 7
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 0.30300381779670715,
      "learning_rate": 8e-05,
      "loss": 1.2692,
      "step": 8
    },
    {
      "epoch": 0.046753246753246755,
      "grad_norm": 0.33119237422943115,
      "learning_rate": 9e-05,
      "loss": 1.3356,
      "step": 9
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.28153595328330994,
      "learning_rate": 0.0001,
      "loss": 1.1681,
      "step": 10
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.4325452148914337,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.3646,
      "step": 11
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 0.43212607502937317,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.3236,
      "step": 12
    },
    {
      "epoch": 0.06753246753246753,
      "grad_norm": 0.39351075887680054,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.2301,
      "step": 13
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.3731982409954071,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2337,
      "step": 14
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 0.34622952342033386,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2392,
      "step": 15
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 0.373747855424881,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3094,
      "step": 16
    },
    {
      "epoch": 0.08831168831168831,
      "grad_norm": 0.3230806291103363,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.1379,
      "step": 17
    },
    {
      "epoch": 0.09350649350649351,
      "grad_norm": 0.36096540093421936,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.3651,
      "step": 18
    },
    {
      "epoch": 0.0987012987012987,
      "grad_norm": 0.35373595356941223,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4041,
      "step": 19
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.3317319452762604,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3334,
      "step": 20
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.35586485266685486,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.3277,
      "step": 21
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.3231983780860901,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2227,
      "step": 22
    },
    {
      "epoch": 0.11948051948051948,
      "grad_norm": 0.3345981538295746,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2484,
      "step": 23
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 0.3658851385116577,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.2305,
      "step": 24
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.37067246437072754,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.131,
      "step": 25
    },
    {
      "epoch": 0.13506493506493505,
      "grad_norm": 0.40390706062316895,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.289,
      "step": 26
    },
    {
      "epoch": 0.14025974025974025,
      "grad_norm": 0.3715671896934509,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.1788,
      "step": 27
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.3955548405647278,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4516,
      "step": 28
    },
    {
      "epoch": 0.15064935064935064,
      "grad_norm": 0.4545679986476898,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.5039,
      "step": 29
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 0.39818987250328064,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2946,
      "step": 30
    },
    {
      "epoch": 0.16103896103896104,
      "grad_norm": 0.4657442271709442,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.4087,
      "step": 31
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 0.47173669934272766,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2468,
      "step": 32
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.40042179822921753,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.1191,
      "step": 33
    },
    {
      "epoch": 0.17662337662337663,
      "grad_norm": 0.4369649887084961,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.3715,
      "step": 34
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.47712573409080505,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2312,
      "step": 35
    },
    {
      "epoch": 0.18701298701298702,
      "grad_norm": 0.5139972567558289,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5135,
      "step": 36
    },
    {
      "epoch": 0.19220779220779222,
      "grad_norm": 0.4982706904411316,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2006,
      "step": 37
    },
    {
      "epoch": 0.1974025974025974,
      "grad_norm": 0.485422283411026,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.3658,
      "step": 38
    },
    {
      "epoch": 0.2025974025974026,
      "grad_norm": 0.49507665634155273,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2338,
      "step": 39
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.5692687034606934,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4821,
      "step": 40
    },
    {
      "epoch": 0.21298701298701297,
      "grad_norm": 0.4980921149253845,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.215,
      "step": 41
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.6296183466911316,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4862,
      "step": 42
    },
    {
      "epoch": 0.22337662337662337,
      "grad_norm": 0.6405119895935059,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.2837,
      "step": 43
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.7146792411804199,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4082,
      "step": 44
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 0.8238335251808167,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.6744,
      "step": 45
    },
    {
      "epoch": 0.23896103896103896,
      "grad_norm": 0.8879733681678772,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4372,
      "step": 46
    },
    {
      "epoch": 0.24415584415584415,
      "grad_norm": 0.992831826210022,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7714,
      "step": 47
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 1.3995647430419922,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.5566,
      "step": 48
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.34774672985076904,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.2085,
      "step": 49
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.3489333391189575,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2864,
      "step": 50
    },
    {
      "epoch": 0.2597402597402597,
      "eval_loss": 1.3044037818908691,
      "eval_runtime": 31.1095,
      "eval_samples_per_second": 5.24,
      "eval_steps_per_second": 1.318,
      "step": 50
    },
    {
      "epoch": 0.2649350649350649,
      "grad_norm": 0.33038291335105896,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.2938,
      "step": 51
    },
    {
      "epoch": 0.2701298701298701,
      "grad_norm": 0.32780855894088745,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.1114,
      "step": 52
    },
    {
      "epoch": 0.2753246753246753,
      "grad_norm": 0.32513588666915894,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.2657,
      "step": 53
    },
    {
      "epoch": 0.2805194805194805,
      "grad_norm": 0.31361356377601624,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.2757,
      "step": 54
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.3155638575553894,
      "learning_rate": 5e-05,
      "loss": 1.2063,
      "step": 55
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.31585606932640076,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.0867,
      "step": 56
    },
    {
      "epoch": 0.2961038961038961,
      "grad_norm": 0.3095378577709198,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.1155,
      "step": 57
    },
    {
      "epoch": 0.3012987012987013,
      "grad_norm": 0.31880173087120056,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3034,
      "step": 58
    },
    {
      "epoch": 0.3064935064935065,
      "grad_norm": 0.3153369724750519,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.1679,
      "step": 59
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.3115677535533905,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.1694,
      "step": 60
    },
    {
      "epoch": 0.3168831168831169,
      "grad_norm": 0.3476245403289795,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.2466,
      "step": 61
    },
    {
      "epoch": 0.3220779220779221,
      "grad_norm": 0.3204329311847687,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.2314,
      "step": 62
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.31050464510917664,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.1565,
      "step": 63
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 0.3489195704460144,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.231,
      "step": 64
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 0.31092599034309387,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.9795,
      "step": 65
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3266049325466156,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1326,
      "step": 66
    },
    {
      "epoch": 0.34805194805194806,
      "grad_norm": 0.34862658381462097,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.0544,
      "step": 67
    },
    {
      "epoch": 0.35324675324675325,
      "grad_norm": 0.3720819056034088,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.2346,
      "step": 68
    },
    {
      "epoch": 0.35844155844155845,
      "grad_norm": 0.3748229444026947,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.2632,
      "step": 69
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.3992089629173279,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.2955,
      "step": 70
    },
    {
      "epoch": 0.36883116883116884,
      "grad_norm": 0.3803309500217438,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.137,
      "step": 71
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 0.41548168659210205,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.3413,
      "step": 72
    },
    {
      "epoch": 0.37922077922077924,
      "grad_norm": 0.4588744044303894,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4306,
      "step": 73
    },
    {
      "epoch": 0.38441558441558443,
      "grad_norm": 0.4805556833744049,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.277,
      "step": 74
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.4144364595413208,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.1136,
      "step": 75
    },
    {
      "epoch": 0.3948051948051948,
      "grad_norm": 0.46915677189826965,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.2499,
      "step": 76
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5677196979522705,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.3259,
      "step": 77
    },
    {
      "epoch": 0.4051948051948052,
      "grad_norm": 0.5241764783859253,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.2467,
      "step": 78
    },
    {
      "epoch": 0.4103896103896104,
      "grad_norm": 0.5175052285194397,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.2434,
      "step": 79
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.47252026200294495,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.261,
      "step": 80
    },
    {
      "epoch": 0.42077922077922075,
      "grad_norm": 0.49494829773902893,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.2451,
      "step": 81
    },
    {
      "epoch": 0.42597402597402595,
      "grad_norm": 0.5081787109375,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2701,
      "step": 82
    },
    {
      "epoch": 0.43116883116883115,
      "grad_norm": 0.501038134098053,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.2223,
      "step": 83
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.5236621499061584,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3133,
      "step": 84
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 0.5346829295158386,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.2814,
      "step": 85
    },
    {
      "epoch": 0.44675324675324674,
      "grad_norm": 0.602837085723877,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.3313,
      "step": 86
    },
    {
      "epoch": 0.45194805194805193,
      "grad_norm": 0.628185510635376,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.3623,
      "step": 87
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.6955432891845703,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.3763,
      "step": 88
    },
    {
      "epoch": 0.4623376623376623,
      "grad_norm": 0.6017211675643921,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.2264,
      "step": 89
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.7660609483718872,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.3396,
      "step": 90
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.6864474415779114,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3113,
      "step": 91
    },
    {
      "epoch": 0.4779220779220779,
      "grad_norm": 0.8158310055732727,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4984,
      "step": 92
    },
    {
      "epoch": 0.4831168831168831,
      "grad_norm": 0.8039913177490234,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.3747,
      "step": 93
    },
    {
      "epoch": 0.4883116883116883,
      "grad_norm": 0.9546723961830139,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5949,
      "step": 94
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 1.4390336275100708,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.7096,
      "step": 95
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 1.3720232248306274,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.923,
      "step": 96
    },
    {
      "epoch": 0.5038961038961038,
      "grad_norm": 0.26757583022117615,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0475,
      "step": 97
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.30529433488845825,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.201,
      "step": 98
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2671392261981964,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0222,
      "step": 99
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.2957288920879364,
      "learning_rate": 0.0,
      "loss": 1.2382,
      "step": 100
    },
    {
      "epoch": 0.5194805194805194,
      "eval_loss": 1.2729405164718628,
      "eval_runtime": 31.7043,
      "eval_samples_per_second": 5.141,
      "eval_steps_per_second": 1.293,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.589344683819008e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}