{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.704225352112676,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014084507042253521,
      "grad_norm": NaN,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "eval_loss": NaN,
      "eval_runtime": 4.2485,
      "eval_samples_per_second": 11.769,
      "eval_steps_per_second": 1.648,
      "step": 1
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": NaN,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": NaN,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": NaN,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": NaN,
      "learning_rate": 0.00015,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": NaN,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": NaN,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": NaN,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": NaN,
      "learning_rate": 0.00027,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": NaN,
      "learning_rate": 0.00029995751920396937,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": NaN,
      "learning_rate": 0.0002998301008774512,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": NaN,
      "learning_rate": 0.000299617817191538,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": NaN,
      "learning_rate": 0.0002993207883859627,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": NaN,
      "learning_rate": 0.00029893918270099324,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": NaN,
      "learning_rate": 0.0002984732162821399,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": NaN,
      "learning_rate": 0.00029792315305772796,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": NaN,
      "learning_rate": 0.00029728930458940595,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": NaN,
      "learning_rate": 0.00029657202989567393,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": NaN,
      "learning_rate": 0.00029577173524853123,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": NaN,
      "learning_rate": 0.0002948888739433602,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": NaN,
      "learning_rate": 0.0002939239460421746,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": NaN,
      "learning_rate": 0.00029287749809037904,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": NaN,
      "learning_rate": 0.00029175012280720024,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": NaN,
      "learning_rate": 0.00029054245874996426,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.352112676056338,
      "eval_loss": NaN,
      "eval_runtime": 3.7691,
      "eval_samples_per_second": 13.266,
      "eval_steps_per_second": 1.857,
      "step": 25
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": NaN,
      "learning_rate": 0.0002892551899524109,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": NaN,
      "learning_rate": 0.0002878890455372498,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": NaN,
      "learning_rate": 0.00028644479930317775,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": NaN,
      "learning_rate": 0.00028492326928659045,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": NaN,
      "learning_rate": 0.0002833253172982385,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": NaN,
      "learning_rate": 0.0002816518484350883,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": NaN,
      "learning_rate": 0.0002799038105676658,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": NaN,
      "learning_rate": 0.00027808219380317216,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": NaN,
      "learning_rate": 0.0002761880299246772,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": NaN,
      "learning_rate": 0.0002742223918067056,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": NaN,
      "learning_rate": 0.0002721863928075503,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": NaN,
      "learning_rate": 0.00027008118613865406,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": NaN,
      "learning_rate": 0.00026790796421141813,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": NaN,
      "learning_rate": 0.0002656679579618081,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": NaN,
      "learning_rate": 0.00026336243615313873,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": NaN,
      "learning_rate": 0.00026099270465743254,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": NaN,
      "learning_rate": 0.0002585601057157605,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": NaN,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": NaN,
      "learning_rate": 0.0002535118517223168,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": NaN,
      "learning_rate": 0.0002508990560551879,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": NaN,
      "learning_rate": 0.00024822911009179276,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": NaN,
      "learning_rate": 0.0002455035261178632,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": NaN,
      "learning_rate": 0.00024272384793309077,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": NaN,
      "learning_rate": 0.00023989164997670202,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": NaN,
      "learning_rate": 0.0002370085364356797,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.704225352112676,
      "eval_loss": NaN,
      "eval_runtime": 3.7681,
      "eval_samples_per_second": 13.269,
      "eval_steps_per_second": 1.858,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 142,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.47075947986944e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}