{
  "best_metric": 1.2665033340454102,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.03388681802778719,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013554727211114877,
      "grad_norm": 36.596012115478516,
      "learning_rate": 5e-05,
      "loss": 63.4065,
      "step": 1
    },
    {
      "epoch": 0.0013554727211114877,
      "eval_loss": 3.8362667560577393,
      "eval_runtime": 213.6984,
      "eval_samples_per_second": 23.257,
      "eval_steps_per_second": 2.911,
      "step": 1
    },
    {
      "epoch": 0.0027109454422229754,
      "grad_norm": 38.99151611328125,
      "learning_rate": 0.0001,
      "loss": 64.8437,
      "step": 2
    },
    {
      "epoch": 0.004066418163334463,
      "grad_norm": 41.29121017456055,
      "learning_rate": 9.989294616193017e-05,
      "loss": 65.1126,
      "step": 3
    },
    {
      "epoch": 0.005421890884445951,
      "grad_norm": 42.77500534057617,
      "learning_rate": 9.957224306869053e-05,
      "loss": 60.8543,
      "step": 4
    },
    {
      "epoch": 0.006777363605557438,
      "grad_norm": 32.83053207397461,
      "learning_rate": 9.903926402016153e-05,
      "loss": 49.4978,
      "step": 5
    },
    {
      "epoch": 0.008132836326668925,
      "grad_norm": 38.703086853027344,
      "learning_rate": 9.829629131445342e-05,
      "loss": 46.339,
      "step": 6
    },
    {
      "epoch": 0.009488309047780414,
      "grad_norm": 42.6236572265625,
      "learning_rate": 9.73465064747553e-05,
      "loss": 41.951,
      "step": 7
    },
    {
      "epoch": 0.010843781768891902,
      "grad_norm": 30.51891326904297,
      "learning_rate": 9.619397662556435e-05,
      "loss": 35.5313,
      "step": 8
    },
    {
      "epoch": 0.012199254490003388,
      "grad_norm": 36.923702239990234,
      "learning_rate": 9.484363707663442e-05,
      "loss": 31.8236,
      "step": 9
    },
    {
      "epoch": 0.013554727211114876,
      "grad_norm": 21.106178283691406,
      "learning_rate": 9.330127018922194e-05,
      "loss": 32.1737,
      "step": 10
    },
    {
      "epoch": 0.014910199932226365,
      "grad_norm": 37.03933334350586,
      "learning_rate": 9.157348061512727e-05,
      "loss": 27.7951,
      "step": 11
    },
    {
      "epoch": 0.01626567265333785,
      "grad_norm": 50.268577575683594,
      "learning_rate": 8.966766701456177e-05,
      "loss": 28.1014,
      "step": 12
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 61.605918884277344,
      "learning_rate": 8.759199037394887e-05,
      "loss": 28.6188,
      "step": 13
    },
    {
      "epoch": 0.018976618095560827,
      "grad_norm": 214.79013061523438,
      "learning_rate": 8.535533905932738e-05,
      "loss": 25.8743,
      "step": 14
    },
    {
      "epoch": 0.020332090816672314,
      "grad_norm": 451.5144348144531,
      "learning_rate": 8.296729075500344e-05,
      "loss": 28.1142,
      "step": 15
    },
    {
      "epoch": 0.021687563537783804,
      "grad_norm": 292.95025634765625,
      "learning_rate": 8.043807145043604e-05,
      "loss": 28.5825,
      "step": 16
    },
    {
      "epoch": 0.02304303625889529,
      "grad_norm": 254.0452880859375,
      "learning_rate": 7.777851165098012e-05,
      "loss": 28.3858,
      "step": 17
    },
    {
      "epoch": 0.024398508980006776,
      "grad_norm": 75.8310775756836,
      "learning_rate": 7.500000000000001e-05,
      "loss": 26.6884,
      "step": 18
    },
    {
      "epoch": 0.025753981701118266,
      "grad_norm": 60.58232116699219,
      "learning_rate": 7.211443451095007e-05,
      "loss": 27.6412,
      "step": 19
    },
    {
      "epoch": 0.027109454422229753,
      "grad_norm": 39.16401290893555,
      "learning_rate": 6.91341716182545e-05,
      "loss": 24.6649,
      "step": 20
    },
    {
      "epoch": 0.02846492714334124,
      "grad_norm": 32.388431549072266,
      "learning_rate": 6.607197326515808e-05,
      "loss": 25.1232,
      "step": 21
    },
    {
      "epoch": 0.02982039986445273,
      "grad_norm": 22.858781814575195,
      "learning_rate": 6.294095225512603e-05,
      "loss": 21.7579,
      "step": 22
    },
    {
      "epoch": 0.031175872585564215,
      "grad_norm": 17.251733779907227,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 21.4803,
      "step": 23
    },
    {
      "epoch": 0.0325313453066757,
      "grad_norm": 20.60053825378418,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 20.8267,
      "step": 24
    },
    {
      "epoch": 0.03388681802778719,
      "grad_norm": 22.706756591796875,
      "learning_rate": 5.327015646150716e-05,
      "loss": 22.8192,
      "step": 25
    },
    {
      "epoch": 0.03388681802778719,
      "eval_loss": 1.2665033340454102,
      "eval_runtime": 213.7001,
      "eval_samples_per_second": 23.257,
      "eval_steps_per_second": 2.911,
      "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": 2.629578157719552e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}