{
  "best_metric": 10.358575820922852,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.272108843537415,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010884353741496598,
      "grad_norm": 0.29789671301841736,
      "learning_rate": 5e-05,
      "loss": 10.3846,
      "step": 1
    },
    {
      "epoch": 0.010884353741496598,
      "eval_loss": 10.38390064239502,
      "eval_runtime": 0.6508,
      "eval_samples_per_second": 951.109,
      "eval_steps_per_second": 119.849,
      "step": 1
    },
    {
      "epoch": 0.021768707482993196,
      "grad_norm": 0.2871239483356476,
      "learning_rate": 0.0001,
      "loss": 10.3839,
      "step": 2
    },
    {
      "epoch": 0.0326530612244898,
      "grad_norm": 0.29564058780670166,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3841,
      "step": 3
    },
    {
      "epoch": 0.04353741496598639,
      "grad_norm": 0.297428697347641,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3827,
      "step": 4
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 0.30088019371032715,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3804,
      "step": 5
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.2966240346431732,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.38,
      "step": 6
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.30285754799842834,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3788,
      "step": 7
    },
    {
      "epoch": 0.08707482993197278,
      "grad_norm": 0.3085600435733795,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3783,
      "step": 8
    },
    {
      "epoch": 0.09795918367346938,
      "grad_norm": 0.3070805072784424,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3761,
      "step": 9
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 0.3117634952068329,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3744,
      "step": 10
    },
    {
      "epoch": 0.11972789115646258,
      "grad_norm": 0.33045291900634766,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.3738,
      "step": 11
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": 0.331281840801239,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.372,
      "step": 12
    },
    {
      "epoch": 0.1414965986394558,
      "grad_norm": 0.32997581362724304,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3734,
      "step": 13
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.3284686803817749,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3721,
      "step": 14
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.34724903106689453,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3708,
      "step": 15
    },
    {
      "epoch": 0.17414965986394557,
      "grad_norm": 0.35911825299263,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3689,
      "step": 16
    },
    {
      "epoch": 0.18503401360544217,
      "grad_norm": 0.3483351469039917,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3674,
      "step": 17
    },
    {
      "epoch": 0.19591836734693877,
      "grad_norm": 0.35687845945358276,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3663,
      "step": 18
    },
    {
      "epoch": 0.20680272108843537,
      "grad_norm": 0.3608298897743225,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3649,
      "step": 19
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 0.36443498730659485,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3643,
      "step": 20
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.3776651620864868,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3623,
      "step": 21
    },
    {
      "epoch": 0.23945578231292516,
      "grad_norm": 0.37512120604515076,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3611,
      "step": 22
    },
    {
      "epoch": 0.2503401360544218,
      "grad_norm": 0.3709583580493927,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3608,
      "step": 23
    },
    {
      "epoch": 0.2612244897959184,
      "grad_norm": 0.3929137885570526,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3592,
      "step": 24
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.370810866355896,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3597,
      "step": 25
    },
    {
      "epoch": 0.272108843537415,
      "eval_loss": 10.358575820922852,
      "eval_runtime": 0.6466,
      "eval_samples_per_second": 957.305,
      "eval_steps_per_second": 120.63,
      "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": 21384029798400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}