{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5322338830584707,
  "eval_steps": 25,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0074962518740629685,
      "grad_norm": NaN,
      "learning_rate": 0.00015,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0074962518740629685,
      "eval_loss": NaN,
      "eval_runtime": 0.1645,
      "eval_samples_per_second": 303.862,
      "eval_steps_per_second": 18.232,
      "step": 1
    },
    {
      "epoch": 0.014992503748125937,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.022488755622188907,
      "grad_norm": NaN,
      "learning_rate": 0.0002998600959423082,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.029985007496251874,
      "grad_norm": NaN,
      "learning_rate": 0.0002994406737417567,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.037481259370314844,
      "grad_norm": NaN,
      "learning_rate": 0.00029874260271490463,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.044977511244377814,
      "grad_norm": NaN,
      "learning_rate": 0.00029776732972055516,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.05247376311844078,
      "grad_norm": NaN,
      "learning_rate": 0.0002965168761609197,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.05997001499250375,
      "grad_norm": NaN,
      "learning_rate": 0.0002949938337919529,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.06746626686656672,
      "grad_norm": NaN,
      "learning_rate": 0.0002932013593515431,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.07496251874062969,
      "grad_norm": NaN,
      "learning_rate": 0.00029114316801669057,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.08245877061469266,
      "grad_norm": NaN,
      "learning_rate": 0.00028882352570323616,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.08995502248875563,
      "grad_norm": NaN,
      "learning_rate": 0.00028624724022409897,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.09745127436281859,
      "grad_norm": NaN,
      "learning_rate": 0.0002834196513243502,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.10494752623688156,
      "grad_norm": NaN,
      "learning_rate": 0.0002803466196137759,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.11244377811094453,
      "grad_norm": NaN,
      "learning_rate": 0.00027703451441986836,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1199400299850075,
      "grad_norm": NaN,
      "learning_rate": 0.000273490200586422,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.12743628185907047,
      "grad_norm": NaN,
      "learning_rate": 0.00026972102424509665,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.13493253373313344,
      "grad_norm": NaN,
      "learning_rate": 0.00026573479758943753,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.1424287856071964,
      "grad_norm": NaN,
      "learning_rate": 0.0002615397826829114,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.14992503748125938,
      "grad_norm": NaN,
      "learning_rate": 0.0002571446743345183,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.15742128935532235,
      "grad_norm": NaN,
      "learning_rate": 0.00025255858207747205,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.16491754122938532,
      "grad_norm": NaN,
      "learning_rate": 0.0002477910112883017,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": NaN,
      "learning_rate": 0.00024285184348550706,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.17991004497751126,
      "grad_norm": NaN,
      "learning_rate": 0.0002377513158486027,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1874062968515742,
      "grad_norm": NaN,
      "learning_rate": 0.00023249999999999999,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1874062968515742,
      "eval_loss": NaN,
      "eval_runtime": 0.1655,
      "eval_samples_per_second": 302.063,
      "eval_steps_per_second": 18.124,
      "step": 25
    },
    {
      "epoch": 0.19490254872563717,
      "grad_norm": NaN,
      "learning_rate": 0.00022710878009370554,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.20239880059970014,
      "grad_norm": NaN,
      "learning_rate": 0.00022158883025624965,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.2098950524737631,
      "grad_norm": NaN,
      "learning_rate": 0.0002159515914266029,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": NaN,
      "learning_rate": 0.0002102087476430831,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.22488755622188905,
      "grad_norm": NaN,
      "learning_rate": 0.00020437220182640135,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.23238380809595202,
      "grad_norm": NaN,
      "learning_rate": 0.00019845405110904146,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.239880059970015,
      "grad_norm": NaN,
      "learning_rate": 0.00019246656176210558,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.24737631184407796,
      "grad_norm": NaN,
      "learning_rate": 0.0001864221437715939,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.25487256371814093,
      "grad_norm": NaN,
      "learning_rate": 0.0001803333251168141,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.2623688155922039,
      "grad_norm": NaN,
      "learning_rate": 0.00017421272580423058,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.2698650674662669,
      "grad_norm": NaN,
      "learning_rate": 0.00016807303171057425,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.2773613193403298,
      "grad_norm": NaN,
      "learning_rate": 0.00016192696828942573,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.2848575712143928,
      "grad_norm": NaN,
      "learning_rate": 0.00015578727419576942,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.29235382308845576,
      "grad_norm": NaN,
      "learning_rate": 0.00014966667488318586,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.29985007496251875,
      "grad_norm": NaN,
      "learning_rate": 0.00014357785622840606,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.3073463268365817,
      "grad_norm": NaN,
      "learning_rate": 0.00013753343823789445,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.3148425787106447,
      "grad_norm": NaN,
      "learning_rate": 0.00013154594889095854,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.32233883058470764,
      "grad_norm": NaN,
      "learning_rate": 0.00012562779817359865,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.32983508245877063,
      "grad_norm": NaN,
      "learning_rate": 0.00011979125235691685,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.3373313343328336,
      "grad_norm": NaN,
      "learning_rate": 0.00011404840857339706,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": NaN,
      "learning_rate": 0.0001084111697437504,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.3523238380809595,
      "grad_norm": NaN,
      "learning_rate": 0.00010289121990629447,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.3598200899550225,
      "grad_norm": NaN,
      "learning_rate": 9.750000000000003e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.36731634182908546,
      "grad_norm": NaN,
      "learning_rate": 9.22486841513973e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.3748125937031484,
      "grad_norm": NaN,
      "learning_rate": 8.714815651449293e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.3748125937031484,
      "eval_loss": NaN,
      "eval_runtime": 0.1641,
      "eval_samples_per_second": 304.675,
      "eval_steps_per_second": 18.28,
      "step": 50
    },
    {
      "epoch": 0.3823088455772114,
      "grad_norm": NaN,
      "learning_rate": 8.220898871169827e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.38980509745127434,
      "grad_norm": NaN,
      "learning_rate": 7.744141792252794e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.39730134932533734,
      "grad_norm": NaN,
      "learning_rate": 7.285532566548172e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.4047976011994003,
      "grad_norm": NaN,
      "learning_rate": 6.846021731708856e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.4122938530734633,
      "grad_norm": NaN,
      "learning_rate": 6.426520241056245e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.4197901049475262,
      "grad_norm": NaN,
      "learning_rate": 6.0278975754903317e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.4272863568215892,
      "grad_norm": NaN,
      "learning_rate": 5.6509799413577934e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": NaN,
      "learning_rate": 5.296548558013161e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.44227886056971516,
      "grad_norm": NaN,
      "learning_rate": 4.9653380386224046e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.4497751124437781,
      "grad_norm": NaN,
      "learning_rate": 4.658034867564977e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.4572713643178411,
      "grad_norm": NaN,
      "learning_rate": 4.375275977590104e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.46476761619190404,
      "grad_norm": NaN,
      "learning_rate": 4.117647429676387e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.47226386806596704,
      "grad_norm": NaN,
      "learning_rate": 3.885683198330941e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.47976011994003,
      "grad_norm": NaN,
      "learning_rate": 3.679864064845691e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.487256371814093,
      "grad_norm": NaN,
      "learning_rate": 3.500616620804712e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.4947526236881559,
      "grad_norm": NaN,
      "learning_rate": 3.348312383908033e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.5022488755622189,
      "grad_norm": NaN,
      "learning_rate": 3.223267027944483e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.5097451274362819,
      "grad_norm": NaN,
      "learning_rate": 3.125739728509535e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": NaN,
      "learning_rate": 3.055932625824328e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.5247376311844077,
      "grad_norm": NaN,
      "learning_rate": 3.0139904057691777e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.5322338830584707,
      "grad_norm": NaN,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0,
      "step": 71
    }
  ],
  "logging_steps": 1,
  "max_steps": 71,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 1122317107200.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}