{
  "best_metric": 0.985734760761261,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.7130124777183601,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0071301247771836,
      "grad_norm": 1.0823220014572144,
      "learning_rate": 1e-05,
      "loss": 6.6569,
      "step": 1
    },
    {
      "epoch": 0.0071301247771836,
      "eval_loss": 2.150402069091797,
      "eval_runtime": 23.6394,
      "eval_samples_per_second": 10.026,
      "eval_steps_per_second": 1.269,
      "step": 1
    },
    {
      "epoch": 0.0142602495543672,
      "grad_norm": 1.3017756938934326,
      "learning_rate": 2e-05,
      "loss": 7.4693,
      "step": 2
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.8406498432159424,
      "learning_rate": 3e-05,
      "loss": 7.979,
      "step": 3
    },
    {
      "epoch": 0.0285204991087344,
      "grad_norm": 1.9255220890045166,
      "learning_rate": 4e-05,
      "loss": 8.4457,
      "step": 4
    },
    {
      "epoch": 0.035650623885918005,
      "grad_norm": 2.0620336532592773,
      "learning_rate": 5e-05,
      "loss": 8.2665,
      "step": 5
    },
    {
      "epoch": 0.0427807486631016,
      "grad_norm": 2.0017974376678467,
      "learning_rate": 6e-05,
      "loss": 8.0234,
      "step": 6
    },
    {
      "epoch": 0.049910873440285206,
      "grad_norm": 1.9698922634124756,
      "learning_rate": 7e-05,
      "loss": 7.7345,
      "step": 7
    },
    {
      "epoch": 0.0570409982174688,
      "grad_norm": 2.260509729385376,
      "learning_rate": 8e-05,
      "loss": 7.4526,
      "step": 8
    },
    {
      "epoch": 0.06417112299465241,
      "grad_norm": 2.485492467880249,
      "learning_rate": 9e-05,
      "loss": 7.1721,
      "step": 9
    },
    {
      "epoch": 0.07130124777183601,
      "grad_norm": 2.157437801361084,
      "learning_rate": 0.0001,
      "loss": 6.8119,
      "step": 10
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 2.448948621749878,
      "learning_rate": 9.99695413509548e-05,
      "loss": 6.4423,
      "step": 11
    },
    {
      "epoch": 0.0855614973262032,
      "grad_norm": 2.756315231323242,
      "learning_rate": 9.987820251299122e-05,
      "loss": 6.2086,
      "step": 12
    },
    {
      "epoch": 0.09269162210338681,
      "grad_norm": 2.5967438220977783,
      "learning_rate": 9.972609476841367e-05,
      "loss": 6.0689,
      "step": 13
    },
    {
      "epoch": 0.09982174688057041,
      "grad_norm": 2.21612548828125,
      "learning_rate": 9.951340343707852e-05,
      "loss": 5.4971,
      "step": 14
    },
    {
      "epoch": 0.10695187165775401,
      "grad_norm": 2.2803194522857666,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.9092,
      "step": 15
    },
    {
      "epoch": 0.1140819964349376,
      "grad_norm": 2.4728004932403564,
      "learning_rate": 9.890738003669029e-05,
      "loss": 6.0649,
      "step": 16
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.0314323902130127,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.4864,
      "step": 17
    },
    {
      "epoch": 0.12834224598930483,
      "grad_norm": 2.048257827758789,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.4174,
      "step": 18
    },
    {
      "epoch": 0.1354723707664884,
      "grad_norm": 2.128129720687866,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.2619,
      "step": 19
    },
    {
      "epoch": 0.14260249554367202,
      "grad_norm": 1.9913911819458008,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.0575,
      "step": 20
    },
    {
      "epoch": 0.1497326203208556,
      "grad_norm": 1.9190443754196167,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.8892,
      "step": 21
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 1.6445850133895874,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.5256,
      "step": 22
    },
    {
      "epoch": 0.16399286987522282,
      "grad_norm": 1.8742074966430664,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.8064,
      "step": 23
    },
    {
      "epoch": 0.1711229946524064,
      "grad_norm": 1.8904237747192383,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.7587,
      "step": 24
    },
    {
      "epoch": 0.17825311942959002,
      "grad_norm": 1.9763126373291016,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.3992,
      "step": 25
    },
    {
      "epoch": 0.18538324420677363,
      "grad_norm": 1.9289206266403198,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.2309,
      "step": 26
    },
    {
      "epoch": 0.1925133689839572,
      "grad_norm": 1.7819998264312744,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.4531,
      "step": 27
    },
    {
      "epoch": 0.19964349376114082,
      "grad_norm": 1.782440423965454,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.7593,
      "step": 28
    },
    {
      "epoch": 0.20677361853832443,
      "grad_norm": 1.7480669021606445,
      "learning_rate": 8.940053768033609e-05,
      "loss": 3.5102,
      "step": 29
    },
    {
      "epoch": 0.21390374331550802,
      "grad_norm": 2.0515565872192383,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.5653,
      "step": 30
    },
    {
      "epoch": 0.22103386809269163,
      "grad_norm": 1.7866798639297485,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.3327,
      "step": 31
    },
    {
      "epoch": 0.2281639928698752,
      "grad_norm": 2.0945322513580322,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.4173,
      "step": 32
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 2.085531711578369,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.3953,
      "step": 33
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.5686299800872803,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.7318,
      "step": 34
    },
    {
      "epoch": 0.24955436720142601,
      "grad_norm": 3.195141077041626,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.3963,
      "step": 35
    },
    {
      "epoch": 0.25668449197860965,
      "grad_norm": 3.8207287788391113,
      "learning_rate": 8.07830737662829e-05,
      "loss": 5.6455,
      "step": 36
    },
    {
      "epoch": 0.2638146167557932,
      "grad_norm": 3.6521031856536865,
      "learning_rate": 7.938926261462366e-05,
      "loss": 6.3745,
      "step": 37
    },
    {
      "epoch": 0.2709447415329768,
      "grad_norm": 3.1133363246917725,
      "learning_rate": 7.795964517353735e-05,
      "loss": 6.3022,
      "step": 38
    },
    {
      "epoch": 0.27807486631016043,
      "grad_norm": 2.0272369384765625,
      "learning_rate": 7.649596321166024e-05,
      "loss": 6.0136,
      "step": 39
    },
    {
      "epoch": 0.28520499108734404,
      "grad_norm": 1.4717522859573364,
      "learning_rate": 7.500000000000001e-05,
      "loss": 5.7502,
      "step": 40
    },
    {
      "epoch": 0.29233511586452765,
      "grad_norm": 1.413915753364563,
      "learning_rate": 7.347357813929454e-05,
      "loss": 5.1095,
      "step": 41
    },
    {
      "epoch": 0.2994652406417112,
      "grad_norm": 1.3348373174667358,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.7922,
      "step": 42
    },
    {
      "epoch": 0.3065953654188948,
      "grad_norm": 1.3580721616744995,
      "learning_rate": 7.033683215379002e-05,
      "loss": 4.9455,
      "step": 43
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 1.3433594703674316,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.675,
      "step": 44
    },
    {
      "epoch": 0.32085561497326204,
      "grad_norm": 1.2860838174819946,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.2363,
      "step": 45
    },
    {
      "epoch": 0.32798573975044565,
      "grad_norm": 1.2380250692367554,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.2934,
      "step": 46
    },
    {
      "epoch": 0.33511586452762926,
      "grad_norm": 1.2230507135391235,
      "learning_rate": 6.378186779084995e-05,
      "loss": 4.8291,
      "step": 47
    },
    {
      "epoch": 0.3422459893048128,
      "grad_norm": 1.3353351354599,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.2347,
      "step": 48
    },
    {
      "epoch": 0.3493761140819964,
      "grad_norm": 1.3078246116638184,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 4.2804,
      "step": 49
    },
    {
      "epoch": 0.35650623885918004,
      "grad_norm": 1.3531790971755981,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.4055,
      "step": 50
    },
    {
      "epoch": 0.35650623885918004,
      "eval_loss": 1.066644549369812,
      "eval_runtime": 24.0327,
      "eval_samples_per_second": 9.862,
      "eval_steps_per_second": 1.248,
      "step": 50
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.4158107042312622,
      "learning_rate": 5.695865504800327e-05,
      "loss": 4.6554,
      "step": 51
    },
    {
      "epoch": 0.37076648841354726,
      "grad_norm": 1.3614400625228882,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.3879,
      "step": 52
    },
    {
      "epoch": 0.3778966131907308,
      "grad_norm": 1.2782399654388428,
      "learning_rate": 5.348782368720626e-05,
      "loss": 4.2737,
      "step": 53
    },
    {
      "epoch": 0.3850267379679144,
      "grad_norm": 1.2635055780410767,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.0312,
      "step": 54
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.2960742712020874,
      "learning_rate": 5e-05,
      "loss": 4.4185,
      "step": 55
    },
    {
      "epoch": 0.39928698752228164,
      "grad_norm": 1.373910903930664,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.8564,
      "step": 56
    },
    {
      "epoch": 0.40641711229946526,
      "grad_norm": 1.3597720861434937,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.9357,
      "step": 57
    },
    {
      "epoch": 0.41354723707664887,
      "grad_norm": 1.4076162576675415,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.5085,
      "step": 58
    },
    {
      "epoch": 0.4206773618538324,
      "grad_norm": 1.3893558979034424,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.2469,
      "step": 59
    },
    {
      "epoch": 0.42780748663101603,
      "grad_norm": 1.395827054977417,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.2323,
      "step": 60
    },
    {
      "epoch": 0.43493761140819964,
      "grad_norm": 1.3438602685928345,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.8626,
      "step": 61
    },
    {
      "epoch": 0.44206773618538325,
      "grad_norm": 1.4302135705947876,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.0505,
      "step": 62
    },
    {
      "epoch": 0.44919786096256686,
      "grad_norm": 1.4719938039779663,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.0484,
      "step": 63
    },
    {
      "epoch": 0.4563279857397504,
      "grad_norm": 1.6130385398864746,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.185,
      "step": 64
    },
    {
      "epoch": 0.46345811051693403,
      "grad_norm": 1.8266406059265137,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.2009,
      "step": 65
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.9313302040100098,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.1525,
      "step": 66
    },
    {
      "epoch": 0.47771836007130125,
      "grad_norm": 2.423699378967285,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.1436,
      "step": 67
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 2.443610668182373,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.4362,
      "step": 68
    },
    {
      "epoch": 0.4919786096256685,
      "grad_norm": 2.610008955001831,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.2321,
      "step": 69
    },
    {
      "epoch": 0.49910873440285203,
      "grad_norm": 3.1767327785491943,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.209,
      "step": 70
    },
    {
      "epoch": 0.5062388591800356,
      "grad_norm": 2.1577703952789307,
      "learning_rate": 2.350403678833976e-05,
      "loss": 5.3338,
      "step": 71
    },
    {
      "epoch": 0.5133689839572193,
      "grad_norm": 2.098604679107666,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 5.2837,
      "step": 72
    },
    {
      "epoch": 0.5204991087344029,
      "grad_norm": 2.168285608291626,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.5498,
      "step": 73
    },
    {
      "epoch": 0.5276292335115864,
      "grad_norm": 2.237492322921753,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 5.3952,
      "step": 74
    },
    {
      "epoch": 0.5347593582887701,
      "grad_norm": 2.1015090942382812,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 5.1172,
      "step": 75
    },
    {
      "epoch": 0.5418894830659536,
      "grad_norm": 1.8349698781967163,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 4.8605,
      "step": 76
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 1.669671654701233,
      "learning_rate": 1.526708147705013e-05,
      "loss": 4.7191,
      "step": 77
    },
    {
      "epoch": 0.5561497326203209,
      "grad_norm": 1.5524064302444458,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 4.0673,
      "step": 78
    },
    {
      "epoch": 0.5632798573975044,
      "grad_norm": 1.3542040586471558,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 4.3932,
      "step": 79
    },
    {
      "epoch": 0.5704099821746881,
      "grad_norm": 1.2547845840454102,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.0502,
      "step": 80
    },
    {
      "epoch": 0.5775401069518716,
      "grad_norm": 1.199395775794983,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 4.3932,
      "step": 81
    },
    {
      "epoch": 0.5846702317290553,
      "grad_norm": 1.1699484586715698,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.8516,
      "step": 82
    },
    {
      "epoch": 0.5918003565062389,
      "grad_norm": 1.2436898946762085,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.9816,
      "step": 83
    },
    {
      "epoch": 0.5989304812834224,
      "grad_norm": 1.2301483154296875,
      "learning_rate": 7.597595192178702e-06,
      "loss": 4.2743,
      "step": 84
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.1662721633911133,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.3479,
      "step": 85
    },
    {
      "epoch": 0.6131907308377896,
      "grad_norm": 1.154500961303711,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.7961,
      "step": 86
    },
    {
      "epoch": 0.6203208556149733,
      "grad_norm": 1.2171392440795898,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.9442,
      "step": 87
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 1.3039647340774536,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.8009,
      "step": 88
    },
    {
      "epoch": 0.6345811051693404,
      "grad_norm": 1.2364025115966797,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.8085,
      "step": 89
    },
    {
      "epoch": 0.6417112299465241,
      "grad_norm": 1.339046835899353,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.8189,
      "step": 90
    },
    {
      "epoch": 0.6488413547237076,
      "grad_norm": 1.3669147491455078,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.636,
      "step": 91
    },
    {
      "epoch": 0.6559714795008913,
      "grad_norm": 1.4621479511260986,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.6006,
      "step": 92
    },
    {
      "epoch": 0.6631016042780749,
      "grad_norm": 1.3589284420013428,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.5506,
      "step": 93
    },
    {
      "epoch": 0.6702317290552585,
      "grad_norm": 1.483871340751648,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.4198,
      "step": 94
    },
    {
      "epoch": 0.6773618538324421,
      "grad_norm": 1.504876732826233,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.2703,
      "step": 95
    },
    {
      "epoch": 0.6844919786096256,
      "grad_norm": 1.50764000415802,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.1094,
      "step": 96
    },
    {
      "epoch": 0.6916221033868093,
      "grad_norm": 1.628373384475708,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.9344,
      "step": 97
    },
    {
      "epoch": 0.6987522281639929,
      "grad_norm": 1.6594825983047485,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.9435,
      "step": 98
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.6344276666641235,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.7318,
      "step": 99
    },
    {
      "epoch": 0.7130124777183601,
      "grad_norm": 1.735816240310669,
      "learning_rate": 0.0,
      "loss": 2.843,
      "step": 100
    },
    {
      "epoch": 0.7130124777183601,
      "eval_loss": 0.985734760761261,
      "eval_runtime": 24.0148,
      "eval_samples_per_second": 9.869,
      "eval_steps_per_second": 1.249,
      "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": 1.3404874741068595e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}