{
  "best_metric": 1.2220337390899658,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3436426116838488,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 8.785038948059082,
      "learning_rate": 5e-05,
      "loss": 1.7568,
      "step": 1
    },
    {
      "epoch": 0.013745704467353952,
      "eval_loss": 1.69869065284729,
      "eval_runtime": 10.6566,
      "eval_samples_per_second": 45.981,
      "eval_steps_per_second": 5.818,
      "step": 1
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 8.94119644165039,
      "learning_rate": 0.0001,
      "loss": 1.5639,
      "step": 2
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 9.636877059936523,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6319,
      "step": 3
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 8.029925346374512,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.4327,
      "step": 4
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 7.860167503356934,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4608,
      "step": 5
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 5.4412407875061035,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3567,
      "step": 6
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 5.89894962310791,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.3971,
      "step": 7
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 5.186604022979736,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4175,
      "step": 8
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 5.103099822998047,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.3878,
      "step": 9
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 5.33500337600708,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.369,
      "step": 10
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 6.5175461769104,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.421,
      "step": 11
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 6.966541767120361,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3992,
      "step": 12
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 8.68342399597168,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.5289,
      "step": 13
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 9.655024528503418,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3686,
      "step": 14
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 6.294942378997803,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.1776,
      "step": 15
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 4.730772018432617,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.1616,
      "step": 16
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 4.466562271118164,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1928,
      "step": 17
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 4.346698760986328,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1748,
      "step": 18
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 3.3439648151397705,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.1408,
      "step": 19
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 3.6823015213012695,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2258,
      "step": 20
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 3.547337055206299,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2464,
      "step": 21
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 4.661966323852539,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.2667,
      "step": 22
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 3.798068046569824,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.2766,
      "step": 23
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 5.671876907348633,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.3518,
      "step": 24
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 8.123512268066406,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.3007,
      "step": 25
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 1.2220337390899658,
      "eval_runtime": 10.6468,
      "eval_samples_per_second": 46.023,
      "eval_steps_per_second": 5.823,
      "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": 1.48820921749078e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}