{
  "best_metric": 1.1823816299438477,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.08547008547008547,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008547008547008547,
      "grad_norm": 3.1805484294891357,
      "learning_rate": 5e-06,
      "loss": 1.8797,
      "step": 1
    },
    {
      "epoch": 0.0008547008547008547,
      "eval_loss": 2.3387086391448975,
      "eval_runtime": 158.3509,
      "eval_samples_per_second": 12.447,
      "eval_steps_per_second": 6.227,
      "step": 1
    },
    {
      "epoch": 0.0017094017094017094,
      "grad_norm": 3.131136178970337,
      "learning_rate": 1e-05,
      "loss": 1.8817,
      "step": 2
    },
    {
      "epoch": 0.002564102564102564,
      "grad_norm": 3.2334909439086914,
      "learning_rate": 1.5e-05,
      "loss": 1.8555,
      "step": 3
    },
    {
      "epoch": 0.003418803418803419,
      "grad_norm": 3.2014031410217285,
      "learning_rate": 2e-05,
      "loss": 1.9768,
      "step": 4
    },
    {
      "epoch": 0.004273504273504274,
      "grad_norm": 3.144679069519043,
      "learning_rate": 2.5e-05,
      "loss": 1.8254,
      "step": 5
    },
    {
      "epoch": 0.005128205128205128,
      "grad_norm": 2.757643938064575,
      "learning_rate": 3e-05,
      "loss": 1.6982,
      "step": 6
    },
    {
      "epoch": 0.005982905982905983,
      "grad_norm": 2.409173011779785,
      "learning_rate": 3.5e-05,
      "loss": 1.6934,
      "step": 7
    },
    {
      "epoch": 0.006837606837606838,
      "grad_norm": 2.4808759689331055,
      "learning_rate": 4e-05,
      "loss": 1.5931,
      "step": 8
    },
    {
      "epoch": 0.007692307692307693,
      "grad_norm": 2.5024032592773438,
      "learning_rate": 4.5e-05,
      "loss": 1.5847,
      "step": 9
    },
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 2.4045209884643555,
      "learning_rate": 5e-05,
      "loss": 1.4925,
      "step": 10
    },
    {
      "epoch": 0.009401709401709401,
      "grad_norm": 2.1205084323883057,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.4824,
      "step": 11
    },
    {
      "epoch": 0.010256410256410256,
      "grad_norm": 1.8501536846160889,
      "learning_rate": 6e-05,
      "loss": 1.3244,
      "step": 12
    },
    {
      "epoch": 0.011111111111111112,
      "grad_norm": 2.3386030197143555,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.2901,
      "step": 13
    },
    {
      "epoch": 0.011965811965811967,
      "grad_norm": 1.988675594329834,
      "learning_rate": 7e-05,
      "loss": 1.2444,
      "step": 14
    },
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 1.7909438610076904,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2972,
      "step": 15
    },
    {
      "epoch": 0.013675213675213675,
      "grad_norm": 1.4051427841186523,
      "learning_rate": 8e-05,
      "loss": 1.2253,
      "step": 16
    },
    {
      "epoch": 0.01452991452991453,
      "grad_norm": 1.5405033826828003,
      "learning_rate": 8.5e-05,
      "loss": 1.2498,
      "step": 17
    },
    {
      "epoch": 0.015384615384615385,
      "grad_norm": 1.4913413524627686,
      "learning_rate": 9e-05,
      "loss": 1.189,
      "step": 18
    },
    {
      "epoch": 0.01623931623931624,
      "grad_norm": 1.3584513664245605,
      "learning_rate": 9.5e-05,
      "loss": 1.1855,
      "step": 19
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 1.367083191871643,
      "learning_rate": 0.0001,
      "loss": 1.1317,
      "step": 20
    },
    {
      "epoch": 0.017948717948717947,
      "grad_norm": 1.4375312328338623,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.2252,
      "step": 21
    },
    {
      "epoch": 0.018803418803418803,
      "grad_norm": 1.6214854717254639,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.1553,
      "step": 22
    },
    {
      "epoch": 0.019658119658119658,
      "grad_norm": 1.416808009147644,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.1797,
      "step": 23
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 1.3466039896011353,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1045,
      "step": 24
    },
    {
      "epoch": 0.021367521367521368,
      "grad_norm": 2.529379367828369,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.6615,
      "step": 25
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 3.794412136077881,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8285,
      "step": 26
    },
    {
      "epoch": 0.023076923076923078,
      "grad_norm": 2.9909701347351074,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.7011,
      "step": 27
    },
    {
      "epoch": 0.023931623931623933,
      "grad_norm": 2.5404868125915527,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.5162,
      "step": 28
    },
    {
      "epoch": 0.024786324786324785,
      "grad_norm": 2.522383689880371,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.4015,
      "step": 29
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 2.389418601989746,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5037,
      "step": 30
    },
    {
      "epoch": 0.026495726495726495,
      "grad_norm": 2.1174089908599854,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.3876,
      "step": 31
    },
    {
      "epoch": 0.02735042735042735,
      "grad_norm": 2.155116558074951,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4693,
      "step": 32
    },
    {
      "epoch": 0.028205128205128206,
      "grad_norm": 1.909348964691162,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.266,
      "step": 33
    },
    {
      "epoch": 0.02905982905982906,
      "grad_norm": 1.8438169956207275,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2909,
      "step": 34
    },
    {
      "epoch": 0.029914529914529916,
      "grad_norm": 1.9625940322875977,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3788,
      "step": 35
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 1.8583937883377075,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.3413,
      "step": 36
    },
    {
      "epoch": 0.03162393162393162,
      "grad_norm": 1.944565773010254,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.1792,
      "step": 37
    },
    {
      "epoch": 0.03247863247863248,
      "grad_norm": 1.757062315940857,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2787,
      "step": 38
    },
    {
      "epoch": 0.03333333333333333,
      "grad_norm": 1.7402759790420532,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.2351,
      "step": 39
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.6585428714752197,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0905,
      "step": 40
    },
    {
      "epoch": 0.03504273504273504,
      "grad_norm": 1.7282662391662598,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.2485,
      "step": 41
    },
    {
      "epoch": 0.035897435897435895,
      "grad_norm": 1.683136224746704,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.3005,
      "step": 42
    },
    {
      "epoch": 0.03675213675213675,
      "grad_norm": 1.7148655652999878,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.2015,
      "step": 43
    },
    {
      "epoch": 0.037606837606837605,
      "grad_norm": 1.6501173973083496,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.1974,
      "step": 44
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 1.67305326461792,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.2394,
      "step": 45
    },
    {
      "epoch": 0.039316239316239315,
      "grad_norm": 1.8358076810836792,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1697,
      "step": 46
    },
    {
      "epoch": 0.040170940170940174,
      "grad_norm": 1.9187673330307007,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.196,
      "step": 47
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 1.662703037261963,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.1822,
      "step": 48
    },
    {
      "epoch": 0.04188034188034188,
      "grad_norm": 1.593295931816101,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.0859,
      "step": 49
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 1.5647625923156738,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0734,
      "step": 50
    },
    {
      "epoch": 0.042735042735042736,
      "eval_loss": 1.2753759622573853,
      "eval_runtime": 160.2165,
      "eval_samples_per_second": 12.302,
      "eval_steps_per_second": 6.154,
      "step": 50
    },
    {
      "epoch": 0.04358974358974359,
      "grad_norm": 3.2061870098114014,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.4302,
      "step": 51
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 1.6502684354782104,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3225,
      "step": 52
    },
    {
      "epoch": 0.0452991452991453,
      "grad_norm": 1.1041203737258911,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.2989,
      "step": 53
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.7463825941085815,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.2729,
      "step": 54
    },
    {
      "epoch": 0.04700854700854701,
      "grad_norm": 1.2780969142913818,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.3126,
      "step": 55
    },
    {
      "epoch": 0.04786324786324787,
      "grad_norm": 1.2614237070083618,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1834,
      "step": 56
    },
    {
      "epoch": 0.04871794871794872,
      "grad_norm": 1.0077286958694458,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.2083,
      "step": 57
    },
    {
      "epoch": 0.04957264957264957,
      "grad_norm": 0.9977828860282898,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1614,
      "step": 58
    },
    {
      "epoch": 0.05042735042735043,
      "grad_norm": 0.989231526851654,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.1232,
      "step": 59
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.0418609380722046,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2087,
      "step": 60
    },
    {
      "epoch": 0.05213675213675214,
      "grad_norm": 1.0184895992279053,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.2046,
      "step": 61
    },
    {
      "epoch": 0.05299145299145299,
      "grad_norm": 1.0147963762283325,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1872,
      "step": 62
    },
    {
      "epoch": 0.05384615384615385,
      "grad_norm": 0.9887883067131042,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.1729,
      "step": 63
    },
    {
      "epoch": 0.0547008547008547,
      "grad_norm": 1.005417823791504,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0677,
      "step": 64
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.9510125517845154,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1557,
      "step": 65
    },
    {
      "epoch": 0.05641025641025641,
      "grad_norm": 0.9024305939674377,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.0331,
      "step": 66
    },
    {
      "epoch": 0.05726495726495726,
      "grad_norm": 1.053831934928894,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.161,
      "step": 67
    },
    {
      "epoch": 0.05811965811965812,
      "grad_norm": 0.9654093384742737,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1771,
      "step": 68
    },
    {
      "epoch": 0.05897435897435897,
      "grad_norm": 1.001448631286621,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.1254,
      "step": 69
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.9279631972312927,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0771,
      "step": 70
    },
    {
      "epoch": 0.06068376068376068,
      "grad_norm": 1.0175575017929077,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.0616,
      "step": 71
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 0.9312410354614258,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.0046,
      "step": 72
    },
    {
      "epoch": 0.062393162393162394,
      "grad_norm": 0.9600768089294434,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.0878,
      "step": 73
    },
    {
      "epoch": 0.06324786324786325,
      "grad_norm": 1.008412480354309,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.069,
      "step": 74
    },
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 1.0578328371047974,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.0534,
      "step": 75
    },
    {
      "epoch": 0.06495726495726496,
      "grad_norm": 1.8800052404403687,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.3345,
      "step": 76
    },
    {
      "epoch": 0.06581196581196581,
      "grad_norm": 1.4857513904571533,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.2275,
      "step": 77
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 1.3094754219055176,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2407,
      "step": 78
    },
    {
      "epoch": 0.06752136752136752,
      "grad_norm": 1.5381840467453003,
      "learning_rate": 7.575190374550272e-05,
      "loss": 1.3354,
      "step": 79
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.3986117839813232,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1581,
      "step": 80
    },
    {
      "epoch": 0.06923076923076923,
      "grad_norm": 1.3145384788513184,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.121,
      "step": 81
    },
    {
      "epoch": 0.07008547008547009,
      "grad_norm": 1.4473127126693726,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.2764,
      "step": 82
    },
    {
      "epoch": 0.07094017094017094,
      "grad_norm": 1.4527322053909302,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.1666,
      "step": 83
    },
    {
      "epoch": 0.07179487179487179,
      "grad_norm": 1.3364454507827759,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0724,
      "step": 84
    },
    {
      "epoch": 0.07264957264957266,
      "grad_norm": 1.418134093284607,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.1684,
      "step": 85
    },
    {
      "epoch": 0.0735042735042735,
      "grad_norm": 1.3991276025772095,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.1841,
      "step": 86
    },
    {
      "epoch": 0.07435897435897436,
      "grad_norm": 1.4230297803878784,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.1781,
      "step": 87
    },
    {
      "epoch": 0.07521367521367521,
      "grad_norm": 1.3617968559265137,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.1224,
      "step": 88
    },
    {
      "epoch": 0.07606837606837606,
      "grad_norm": 1.374157428741455,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.099,
      "step": 89
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.4025551080703735,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.2434,
      "step": 90
    },
    {
      "epoch": 0.07777777777777778,
      "grad_norm": 1.4835059642791748,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.2055,
      "step": 91
    },
    {
      "epoch": 0.07863247863247863,
      "grad_norm": 1.4067541360855103,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.202,
      "step": 92
    },
    {
      "epoch": 0.07948717948717948,
      "grad_norm": 1.3524061441421509,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.2138,
      "step": 93
    },
    {
      "epoch": 0.08034188034188035,
      "grad_norm": 1.4857449531555176,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.172,
      "step": 94
    },
    {
      "epoch": 0.0811965811965812,
      "grad_norm": 1.5069938898086548,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1011,
      "step": 95
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 1.3394262790679932,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0926,
      "step": 96
    },
    {
      "epoch": 0.0829059829059829,
      "grad_norm": 1.3197392225265503,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.1411,
      "step": 97
    },
    {
      "epoch": 0.08376068376068375,
      "grad_norm": 1.3767728805541992,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.1834,
      "step": 98
    },
    {
      "epoch": 0.08461538461538462,
      "grad_norm": 1.352771520614624,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.0231,
      "step": 99
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 1.4974371194839478,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0963,
      "step": 100
    },
    {
      "epoch": 0.08547008547008547,
      "eval_loss": 1.1823816299438477,
      "eval_runtime": 160.2027,
      "eval_samples_per_second": 12.303,
      "eval_steps_per_second": 6.155,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.508513578745856e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}