{
  "best_metric": 4.343160152435303,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06817794443497528,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027271177773990113,
      "grad_norm": 23.088069915771484,
      "learning_rate": 5e-05,
      "loss": 6.5334,
      "step": 1
    },
    {
      "epoch": 0.0027271177773990113,
      "eval_loss": 7.971259593963623,
      "eval_runtime": 22.5499,
      "eval_samples_per_second": 109.535,
      "eval_steps_per_second": 13.703,
      "step": 1
    },
    {
      "epoch": 0.005454235554798023,
      "grad_norm": 30.575834274291992,
      "learning_rate": 0.0001,
      "loss": 6.9307,
      "step": 2
    },
    {
      "epoch": 0.008181353332197034,
      "grad_norm": 14.558832168579102,
      "learning_rate": 9.989294616193017e-05,
      "loss": 6.7458,
      "step": 3
    },
    {
      "epoch": 0.010908471109596045,
      "grad_norm": 16.40069580078125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.6478,
      "step": 4
    },
    {
      "epoch": 0.013635588886995058,
      "grad_norm": 9.622591972351074,
      "learning_rate": 9.903926402016153e-05,
      "loss": 6.5382,
      "step": 5
    },
    {
      "epoch": 0.01636270666439407,
      "grad_norm": 12.521501541137695,
      "learning_rate": 9.829629131445342e-05,
      "loss": 6.2893,
      "step": 6
    },
    {
      "epoch": 0.01908982444179308,
      "grad_norm": 15.39205551147461,
      "learning_rate": 9.73465064747553e-05,
      "loss": 5.9134,
      "step": 7
    },
    {
      "epoch": 0.02181694221919209,
      "grad_norm": 11.018770217895508,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.8059,
      "step": 8
    },
    {
      "epoch": 0.0245440599965911,
      "grad_norm": 6.613672733306885,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.6766,
      "step": 9
    },
    {
      "epoch": 0.027271177773990116,
      "grad_norm": 11.29594612121582,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.5396,
      "step": 10
    },
    {
      "epoch": 0.029998295551389127,
      "grad_norm": 8.879044532775879,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.4328,
      "step": 11
    },
    {
      "epoch": 0.03272541332878814,
      "grad_norm": 6.3747148513793945,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.7125,
      "step": 12
    },
    {
      "epoch": 0.03545253110618715,
      "grad_norm": 5.162105083465576,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.8967,
      "step": 13
    },
    {
      "epoch": 0.03817964888358616,
      "grad_norm": 5.629300117492676,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.4827,
      "step": 14
    },
    {
      "epoch": 0.040906766660985174,
      "grad_norm": 3.7468292713165283,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.3707,
      "step": 15
    },
    {
      "epoch": 0.04363388443838418,
      "grad_norm": 3.5975074768066406,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.3395,
      "step": 16
    },
    {
      "epoch": 0.046361002215783195,
      "grad_norm": 3.4473319053649902,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.3609,
      "step": 17
    },
    {
      "epoch": 0.0490881199931822,
      "grad_norm": 4.343530654907227,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.376,
      "step": 18
    },
    {
      "epoch": 0.05181523777058122,
      "grad_norm": 2.6034982204437256,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.3529,
      "step": 19
    },
    {
      "epoch": 0.05454235554798023,
      "grad_norm": 3.1746459007263184,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.44,
      "step": 20
    },
    {
      "epoch": 0.05726947332537924,
      "grad_norm": 2.4300379753112793,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.2706,
      "step": 21
    },
    {
      "epoch": 0.05999659110277825,
      "grad_norm": 2.5436666011810303,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.4469,
      "step": 22
    },
    {
      "epoch": 0.06272370888017727,
      "grad_norm": 2.800977945327759,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.4854,
      "step": 23
    },
    {
      "epoch": 0.06545082665757627,
      "grad_norm": 3.238574504852295,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.5439,
      "step": 24
    },
    {
      "epoch": 0.06817794443497528,
      "grad_norm": 6.476902484893799,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.6658,
      "step": 25
    },
    {
      "epoch": 0.06817794443497528,
      "eval_loss": 4.343160152435303,
      "eval_runtime": 22.5567,
      "eval_samples_per_second": 109.502,
      "eval_steps_per_second": 13.699,
      "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": 4.16708196040704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}