{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06396929473852551,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025587717895410203,
      "grad_norm": 8.334024429321289,
      "learning_rate": 5e-05,
      "loss": 2.6052,
      "step": 1
    },
    {
      "epoch": 0.0025587717895410203,
      "eval_loss": NaN,
      "eval_runtime": 74.5919,
      "eval_samples_per_second": 35.299,
      "eval_steps_per_second": 4.424,
      "step": 1
    },
    {
      "epoch": 0.005117543579082041,
      "grad_norm": 10.940125465393066,
      "learning_rate": 0.0001,
      "loss": 3.3579,
      "step": 2
    },
    {
      "epoch": 0.007676315368623061,
      "grad_norm": 7.787834167480469,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.181,
      "step": 3
    },
    {
      "epoch": 0.010235087158164081,
      "grad_norm": 7.5154948234558105,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.4313,
      "step": 4
    },
    {
      "epoch": 0.012793858947705102,
      "grad_norm": 8.15333080291748,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7125,
      "step": 5
    },
    {
      "epoch": 0.015352630737246123,
      "grad_norm": 6.947421073913574,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0752,
      "step": 6
    },
    {
      "epoch": 0.01791140252678714,
      "grad_norm": 4.807391166687012,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5733,
      "step": 7
    },
    {
      "epoch": 0.020470174316328162,
      "grad_norm": 8.114211082458496,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4164,
      "step": 8
    },
    {
      "epoch": 0.023028946105869183,
      "grad_norm": 3.900653123855591,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2119,
      "step": 9
    },
    {
      "epoch": 0.025587717895410204,
      "grad_norm": 4.901590824127197,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2332,
      "step": 10
    },
    {
      "epoch": 0.028146489684951224,
      "grad_norm": 2.4796481132507324,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1287,
      "step": 11
    },
    {
      "epoch": 0.030705261474492245,
      "grad_norm": 1.9578641653060913,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1035,
      "step": 12
    },
    {
      "epoch": 0.033264033264033266,
      "grad_norm": 3.6358413696289062,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3265,
      "step": 13
    },
    {
      "epoch": 0.03582280505357428,
      "grad_norm": 2.5038394927978516,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1806,
      "step": 14
    },
    {
      "epoch": 0.03838157684311531,
      "grad_norm": 1.8473141193389893,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.126,
      "step": 15
    },
    {
      "epoch": 0.040940348632656325,
      "grad_norm": 2.4110004901885986,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.1401,
      "step": 16
    },
    {
      "epoch": 0.04349912042219734,
      "grad_norm": 1.2881044149398804,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1238,
      "step": 17
    },
    {
      "epoch": 0.046057892211738366,
      "grad_norm": 1.0083253383636475,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.075,
      "step": 18
    },
    {
      "epoch": 0.04861666400127938,
      "grad_norm": 1.9869771003723145,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.07,
      "step": 19
    },
    {
      "epoch": 0.05117543579082041,
      "grad_norm": 1.36537766456604,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0881,
      "step": 20
    },
    {
      "epoch": 0.053734207580361425,
      "grad_norm": 1.1762269735336304,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0692,
      "step": 21
    },
    {
      "epoch": 0.05629297936990245,
      "grad_norm": 2.1188955307006836,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1169,
      "step": 22
    },
    {
      "epoch": 0.058851751159443466,
      "grad_norm": 1.6357115507125854,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0666,
      "step": 23
    },
    {
      "epoch": 0.06141052294898449,
      "grad_norm": 1.2706236839294434,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0406,
      "step": 24
    },
    {
      "epoch": 0.06396929473852551,
      "grad_norm": 2.2332940101623535,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0662,
      "step": 25
    },
    {
      "epoch": 0.06396929473852551,
      "eval_loss": NaN,
      "eval_runtime": 36.4427,
      "eval_samples_per_second": 72.25,
      "eval_steps_per_second": 9.055,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.94731890081792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}