{
  "best_metric": 1.2520782947540283,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0081662651586297,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016332530317259402,
      "grad_norm": 0.7842411994934082,
      "learning_rate": 0.0001,
      "loss": 0.7559,
      "step": 1
    },
    {
      "epoch": 0.00016332530317259402,
      "eval_loss": 1.800525188446045,
      "eval_runtime": 186.0891,
      "eval_samples_per_second": 13.854,
      "eval_steps_per_second": 6.927,
      "step": 1
    },
    {
      "epoch": 0.00032665060634518803,
      "grad_norm": 0.811083972454071,
      "learning_rate": 0.0002,
      "loss": 1.0546,
      "step": 2
    },
    {
      "epoch": 0.0004899759095177821,
      "grad_norm": 0.41595783829689026,
      "learning_rate": 0.00019978589232386035,
      "loss": 1.011,
      "step": 3
    },
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 0.707165539264679,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.9928,
      "step": 4
    },
    {
      "epoch": 0.0008166265158629701,
      "grad_norm": 0.5684491991996765,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.1686,
      "step": 5
    },
    {
      "epoch": 0.0009799518190355642,
      "grad_norm": 1.9615379571914673,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.1679,
      "step": 6
    },
    {
      "epoch": 0.0011432771222081581,
      "grad_norm": 0.8058582544326782,
      "learning_rate": 0.0001946930129495106,
      "loss": 1.1014,
      "step": 7
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 0.5286304950714111,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.0652,
      "step": 8
    },
    {
      "epoch": 0.0014699277285533461,
      "grad_norm": 0.583321213722229,
      "learning_rate": 0.00018968727415326884,
      "loss": 1.1477,
      "step": 9
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 0.519877552986145,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.9294,
      "step": 10
    },
    {
      "epoch": 0.001796578334898534,
      "grad_norm": 0.6650463342666626,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.1209,
      "step": 11
    },
    {
      "epoch": 0.0019599036380711283,
      "grad_norm": 0.6571516990661621,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.051,
      "step": 12
    },
    {
      "epoch": 0.0021232289412437223,
      "grad_norm": 0.7003201246261597,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.0904,
      "step": 13
    },
    {
      "epoch": 0.0022865542444163163,
      "grad_norm": 0.5793249011039734,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.0424,
      "step": 14
    },
    {
      "epoch": 0.0024498795475889103,
      "grad_norm": 0.6923633217811584,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.0452,
      "step": 15
    },
    {
      "epoch": 0.0026132048507615043,
      "grad_norm": 0.6244546175003052,
      "learning_rate": 0.00016087614290087208,
      "loss": 1.0152,
      "step": 16
    },
    {
      "epoch": 0.0027765301539340983,
      "grad_norm": 0.7005864381790161,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.1659,
      "step": 17
    },
    {
      "epoch": 0.0029398554571066922,
      "grad_norm": 0.787933886051178,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2107,
      "step": 18
    },
    {
      "epoch": 0.0031031807602792862,
      "grad_norm": 0.741934597492218,
      "learning_rate": 0.00014422886902190014,
      "loss": 1.0042,
      "step": 19
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 1.0619328022003174,
      "learning_rate": 0.000138268343236509,
      "loss": 1.2475,
      "step": 20
    },
    {
      "epoch": 0.003429831366624474,
      "grad_norm": 0.7181271910667419,
      "learning_rate": 0.00013214394653031616,
      "loss": 1.0462,
      "step": 21
    },
    {
      "epoch": 0.003593156669797068,
      "grad_norm": 0.7589104175567627,
      "learning_rate": 0.00012588190451025207,
      "loss": 1.0575,
      "step": 22
    },
    {
      "epoch": 0.003756481972969662,
      "grad_norm": 0.6586993932723999,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.1049,
      "step": 23
    },
    {
      "epoch": 0.003919807276142257,
      "grad_norm": 0.7785890102386475,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.0885,
      "step": 24
    },
    {
      "epoch": 0.00408313257931485,
      "grad_norm": 0.9171671271324158,
      "learning_rate": 0.00010654031292301432,
      "loss": 1.1892,
      "step": 25
    },
    {
      "epoch": 0.00408313257931485,
      "eval_loss": 1.3473916053771973,
      "eval_runtime": 186.5929,
      "eval_samples_per_second": 13.816,
      "eval_steps_per_second": 6.908,
      "step": 25
    },
    {
      "epoch": 0.004246457882487445,
      "grad_norm": 0.9192604422569275,
      "learning_rate": 0.0001,
      "loss": 1.182,
      "step": 26
    },
    {
      "epoch": 0.004409783185660038,
      "grad_norm": 0.9144134521484375,
      "learning_rate": 9.345968707698569e-05,
      "loss": 1.1901,
      "step": 27
    },
    {
      "epoch": 0.0045731084888326326,
      "grad_norm": 0.9117483496665955,
      "learning_rate": 8.694738077799488e-05,
      "loss": 1.1575,
      "step": 28
    },
    {
      "epoch": 0.004736433792005226,
      "grad_norm": 1.0398228168487549,
      "learning_rate": 8.049096779838719e-05,
      "loss": 1.2178,
      "step": 29
    },
    {
      "epoch": 0.0048997590951778205,
      "grad_norm": 0.9837586283683777,
      "learning_rate": 7.411809548974792e-05,
      "loss": 1.016,
      "step": 30
    },
    {
      "epoch": 0.005063084398350414,
      "grad_norm": 1.0707706212997437,
      "learning_rate": 6.785605346968386e-05,
      "loss": 1.3534,
      "step": 31
    },
    {
      "epoch": 0.0052264097015230085,
      "grad_norm": 1.2883225679397583,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.2281,
      "step": 32
    },
    {
      "epoch": 0.005389735004695602,
      "grad_norm": 0.973362386226654,
      "learning_rate": 5.577113097809989e-05,
      "loss": 1.0841,
      "step": 33
    },
    {
      "epoch": 0.0055530603078681965,
      "grad_norm": 1.18382728099823,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2332,
      "step": 34
    },
    {
      "epoch": 0.005716385611040791,
      "grad_norm": 1.353372573852539,
      "learning_rate": 4.444297669803981e-05,
      "loss": 1.2308,
      "step": 35
    },
    {
      "epoch": 0.0058797109142133845,
      "grad_norm": 1.5076109170913696,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 1.3734,
      "step": 36
    },
    {
      "epoch": 0.006043036217385979,
      "grad_norm": 1.4926120042800903,
      "learning_rate": 3.406541848999312e-05,
      "loss": 1.2896,
      "step": 37
    },
    {
      "epoch": 0.0062063615205585725,
      "grad_norm": 1.3520236015319824,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.2777,
      "step": 38
    },
    {
      "epoch": 0.006369686823731167,
      "grad_norm": 1.809522032737732,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 1.2962,
      "step": 39
    },
    {
      "epoch": 0.0065330121269037604,
      "grad_norm": 1.8173556327819824,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 1.5552,
      "step": 40
    },
    {
      "epoch": 0.006696337430076355,
      "grad_norm": 2.030938148498535,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 1.5041,
      "step": 41
    },
    {
      "epoch": 0.006859662733248948,
      "grad_norm": 2.2760345935821533,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.502,
      "step": 42
    },
    {
      "epoch": 0.007022988036421543,
      "grad_norm": 3.6226515769958496,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 1.8339,
      "step": 43
    },
    {
      "epoch": 0.007186313339594136,
      "grad_norm": 3.4638423919677734,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.6236,
      "step": 44
    },
    {
      "epoch": 0.007349638642766731,
      "grad_norm": 5.1530442237854,
      "learning_rate": 5.306987050489442e-06,
      "loss": 1.895,
      "step": 45
    },
    {
      "epoch": 0.007512963945939324,
      "grad_norm": 4.3372578620910645,
      "learning_rate": 3.40741737109318e-06,
      "loss": 1.6363,
      "step": 46
    },
    {
      "epoch": 0.007676289249111919,
      "grad_norm": 4.029924392700195,
      "learning_rate": 1.921471959676957e-06,
      "loss": 1.799,
      "step": 47
    },
    {
      "epoch": 0.007839614552284513,
      "grad_norm": 6.649318218231201,
      "learning_rate": 8.555138626189618e-07,
      "loss": 2.1027,
      "step": 48
    },
    {
      "epoch": 0.008002939855457107,
      "grad_norm": 7.667248249053955,
      "learning_rate": 2.141076761396521e-07,
      "loss": 2.1851,
      "step": 49
    },
    {
      "epoch": 0.0081662651586297,
      "grad_norm": 9.058297157287598,
      "learning_rate": 0.0,
      "loss": 2.5236,
      "step": 50
    },
    {
      "epoch": 0.0081662651586297,
      "eval_loss": 1.2520782947540283,
      "eval_runtime": 186.6215,
      "eval_samples_per_second": 13.814,
      "eval_steps_per_second": 6.907,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.02936877203456e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}