{
  "best_metric": 11.07034969329834,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.008,
  "eval_steps": 25,
  "global_step": 47,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.064,
      "grad_norm": 2.6855862140655518,
      "learning_rate": 5e-05,
      "loss": 11.0895,
      "step": 1
    },
    {
      "epoch": 0.064,
      "eval_loss": 11.088528633117676,
      "eval_runtime": 0.1072,
      "eval_samples_per_second": 989.152,
      "eval_steps_per_second": 130.643,
      "step": 1
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.2537662982940674,
      "learning_rate": 0.0001,
      "loss": 11.0903,
      "step": 2
    },
    {
      "epoch": 0.192,
      "grad_norm": 3.422922372817993,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.0944,
      "step": 3
    },
    {
      "epoch": 0.256,
      "grad_norm": 3.773242950439453,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.0866,
      "step": 4
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.9546549320220947,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.0927,
      "step": 5
    },
    {
      "epoch": 0.384,
      "grad_norm": 3.305382251739502,
      "learning_rate": 9.806308479691595e-05,
      "loss": 11.0922,
      "step": 6
    },
    {
      "epoch": 0.448,
      "grad_norm": 3.7564594745635986,
      "learning_rate": 9.698463103929542e-05,
      "loss": 11.0857,
      "step": 7
    },
    {
      "epoch": 0.512,
      "grad_norm": 4.157351970672607,
      "learning_rate": 9.567727288213005e-05,
      "loss": 11.0871,
      "step": 8
    },
    {
      "epoch": 0.576,
      "grad_norm": 3.0301969051361084,
      "learning_rate": 9.414737964294636e-05,
      "loss": 11.0898,
      "step": 9
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.1963460445404053,
      "learning_rate": 9.24024048078213e-05,
      "loss": 11.0868,
      "step": 10
    },
    {
      "epoch": 0.704,
      "grad_norm": 3.8943629264831543,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.0849,
      "step": 11
    },
    {
      "epoch": 0.768,
      "grad_norm": 3.321195602416992,
      "learning_rate": 8.83022221559489e-05,
      "loss": 11.0845,
      "step": 12
    },
    {
      "epoch": 0.832,
      "grad_norm": 3.2425730228424072,
      "learning_rate": 8.596699001693255e-05,
      "loss": 11.0834,
      "step": 13
    },
    {
      "epoch": 0.896,
      "grad_norm": 3.6515064239501953,
      "learning_rate": 8.345653031794292e-05,
      "loss": 11.0826,
      "step": 14
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.153082847595215,
      "learning_rate": 8.07830737662829e-05,
      "loss": 11.0781,
      "step": 15
    },
    {
      "epoch": 1.024,
      "grad_norm": 3.426725149154663,
      "learning_rate": 7.795964517353735e-05,
      "loss": 11.087,
      "step": 16
    },
    {
      "epoch": 1.088,
      "grad_norm": 3.846893548965454,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.0825,
      "step": 17
    },
    {
      "epoch": 1.152,
      "grad_norm": 3.9459829330444336,
      "learning_rate": 7.191855733945387e-05,
      "loss": 11.0799,
      "step": 18
    },
    {
      "epoch": 1.216,
      "grad_norm": 5.128429889678955,
      "learning_rate": 6.873032967079561e-05,
      "loss": 11.0772,
      "step": 19
    },
    {
      "epoch": 1.28,
      "grad_norm": 4.148745059967041,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.0813,
      "step": 20
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 3.7526028156280518,
      "learning_rate": 6.209609477998338e-05,
      "loss": 11.0821,
      "step": 21
    },
    {
      "epoch": 1.408,
      "grad_norm": 4.346903324127197,
      "learning_rate": 5.868240888334653e-05,
      "loss": 11.0767,
      "step": 22
    },
    {
      "epoch": 1.472,
      "grad_norm": 5.584142684936523,
      "learning_rate": 5.522642316338268e-05,
      "loss": 11.0749,
      "step": 23
    },
    {
      "epoch": 1.536,
      "grad_norm": 3.646685838699341,
      "learning_rate": 5.174497483512506e-05,
      "loss": 11.0754,
      "step": 24
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.943727731704712,
      "learning_rate": 4.825502516487497e-05,
      "loss": 11.0782,
      "step": 25
    },
    {
      "epoch": 1.6,
      "eval_loss": 11.07034969329834,
      "eval_runtime": 0.1054,
      "eval_samples_per_second": 1005.981,
      "eval_steps_per_second": 132.865,
      "step": 25
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 4.830604553222656,
      "learning_rate": 4.477357683661734e-05,
      "loss": 11.0723,
      "step": 26
    },
    {
      "epoch": 1.728,
      "grad_norm": 5.275437831878662,
      "learning_rate": 4.131759111665349e-05,
      "loss": 11.0776,
      "step": 27
    },
    {
      "epoch": 1.792,
      "grad_norm": 3.4468271732330322,
      "learning_rate": 3.790390522001662e-05,
      "loss": 11.0769,
      "step": 28
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 4.286435604095459,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.0735,
      "step": 29
    },
    {
      "epoch": 1.92,
      "grad_norm": 4.553131580352783,
      "learning_rate": 3.12696703292044e-05,
      "loss": 11.0687,
      "step": 30
    },
    {
      "epoch": 1.984,
      "grad_norm": 4.932947158813477,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 11.0769,
      "step": 31
    },
    {
      "epoch": 2.048,
      "grad_norm": 4.311124801635742,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.0789,
      "step": 32
    },
    {
      "epoch": 2.112,
      "grad_norm": 4.4758620262146,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 11.0791,
      "step": 33
    },
    {
      "epoch": 2.176,
      "grad_norm": 4.808510780334473,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 11.0723,
      "step": 34
    },
    {
      "epoch": 2.24,
      "grad_norm": 6.5858964920043945,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 11.0734,
      "step": 35
    },
    {
      "epoch": 2.304,
      "grad_norm": 3.916059732437134,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 11.079,
      "step": 36
    },
    {
      "epoch": 2.368,
      "grad_norm": 4.540916919708252,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 11.0698,
      "step": 37
    },
    {
      "epoch": 2.432,
      "grad_norm": 5.163912296295166,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.0768,
      "step": 38
    },
    {
      "epoch": 2.496,
      "grad_norm": 5.536440849304199,
      "learning_rate": 7.597595192178702e-06,
      "loss": 11.0735,
      "step": 39
    },
    {
      "epoch": 2.56,
      "grad_norm": 3.9795005321502686,
      "learning_rate": 5.852620357053651e-06,
      "loss": 11.0733,
      "step": 40
    },
    {
      "epoch": 2.624,
      "grad_norm": 4.769349098205566,
      "learning_rate": 4.322727117869951e-06,
      "loss": 11.0765,
      "step": 41
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 5.8106465339660645,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 11.0647,
      "step": 42
    },
    {
      "epoch": 2.752,
      "grad_norm": 5.031451225280762,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 11.0743,
      "step": 43
    },
    {
      "epoch": 2.816,
      "grad_norm": 4.750061988830566,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 11.07,
      "step": 44
    },
    {
      "epoch": 2.88,
      "grad_norm": 5.097783088684082,
      "learning_rate": 4.865965629214819e-07,
      "loss": 11.0777,
      "step": 45
    },
    {
      "epoch": 2.944,
      "grad_norm": 6.31856632232666,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 11.0714,
      "step": 46
    },
    {
      "epoch": 3.008,
      "grad_norm": 3.7459287643432617,
      "learning_rate": 0.0,
      "loss": 11.0713,
      "step": 47
    }
  ],
  "logging_steps": 1,
  "max_steps": 47,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3950531051520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}