{
  "best_metric": 3.657539129257202,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0042866941015089165,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017146776406035664,
      "grad_norm": 82.31401824951172,
      "learning_rate": 2e-05,
      "loss": 15.6851,
      "step": 1
    },
    {
      "epoch": 0.00017146776406035664,
      "eval_loss": 4.125166416168213,
      "eval_runtime": 200.3227,
      "eval_samples_per_second": 12.26,
      "eval_steps_per_second": 6.13,
      "step": 1
    },
    {
      "epoch": 0.0003429355281207133,
      "grad_norm": 49.468082427978516,
      "learning_rate": 4e-05,
      "loss": 17.2801,
      "step": 2
    },
    {
      "epoch": 0.00051440329218107,
      "grad_norm": 64.14324951171875,
      "learning_rate": 6e-05,
      "loss": 15.4988,
      "step": 3
    },
    {
      "epoch": 0.0006858710562414266,
      "grad_norm": 47.32133865356445,
      "learning_rate": 8e-05,
      "loss": 17.743,
      "step": 4
    },
    {
      "epoch": 0.0008573388203017832,
      "grad_norm": 58.300575256347656,
      "learning_rate": 0.0001,
      "loss": 14.9927,
      "step": 5
    },
    {
      "epoch": 0.0008573388203017832,
      "eval_loss": 4.102006435394287,
      "eval_runtime": 206.3193,
      "eval_samples_per_second": 11.904,
      "eval_steps_per_second": 5.952,
      "step": 5
    },
    {
      "epoch": 0.00102880658436214,
      "grad_norm": 62.37811279296875,
      "learning_rate": 0.00012,
      "loss": 18.3138,
      "step": 6
    },
    {
      "epoch": 0.0012002743484224967,
      "grad_norm": 54.84489059448242,
      "learning_rate": 0.00014,
      "loss": 17.7092,
      "step": 7
    },
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 53.065765380859375,
      "learning_rate": 0.00016,
      "loss": 18.5554,
      "step": 8
    },
    {
      "epoch": 0.0015432098765432098,
      "grad_norm": 58.191566467285156,
      "learning_rate": 0.00018,
      "loss": 17.6219,
      "step": 9
    },
    {
      "epoch": 0.0017146776406035665,
      "grad_norm": 43.95583724975586,
      "learning_rate": 0.0002,
      "loss": 16.3122,
      "step": 10
    },
    {
      "epoch": 0.0017146776406035665,
      "eval_loss": 3.971724510192871,
      "eval_runtime": 206.466,
      "eval_samples_per_second": 11.895,
      "eval_steps_per_second": 5.948,
      "step": 10
    },
    {
      "epoch": 0.0018861454046639231,
      "grad_norm": 74.35279083251953,
      "learning_rate": 0.00019781476007338058,
      "loss": 13.9742,
      "step": 11
    },
    {
      "epoch": 0.00205761316872428,
      "grad_norm": 71.51895141601562,
      "learning_rate": 0.0001913545457642601,
      "loss": 15.6666,
      "step": 12
    },
    {
      "epoch": 0.0022290809327846365,
      "grad_norm": 65.90678405761719,
      "learning_rate": 0.00018090169943749476,
      "loss": 15.632,
      "step": 13
    },
    {
      "epoch": 0.0024005486968449933,
      "grad_norm": 68.94075775146484,
      "learning_rate": 0.00016691306063588583,
      "loss": 18.9844,
      "step": 14
    },
    {
      "epoch": 0.00257201646090535,
      "grad_norm": 67.19559478759766,
      "learning_rate": 0.00015000000000000001,
      "loss": 14.3089,
      "step": 15
    },
    {
      "epoch": 0.00257201646090535,
      "eval_loss": 3.7722387313842773,
      "eval_runtime": 206.3715,
      "eval_samples_per_second": 11.901,
      "eval_steps_per_second": 5.95,
      "step": 15
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 87.80136108398438,
      "learning_rate": 0.00013090169943749476,
      "loss": 17.8558,
      "step": 16
    },
    {
      "epoch": 0.002914951989026063,
      "grad_norm": 63.244606018066406,
      "learning_rate": 0.00011045284632676536,
      "loss": 16.5816,
      "step": 17
    },
    {
      "epoch": 0.0030864197530864196,
      "grad_norm": 66.2993392944336,
      "learning_rate": 8.954715367323468e-05,
      "loss": 15.0449,
      "step": 18
    },
    {
      "epoch": 0.0032578875171467765,
      "grad_norm": 80.09910583496094,
      "learning_rate": 6.909830056250527e-05,
      "loss": 14.8124,
      "step": 19
    },
    {
      "epoch": 0.003429355281207133,
      "grad_norm": 53.13572311401367,
      "learning_rate": 5.000000000000002e-05,
      "loss": 15.4691,
      "step": 20
    },
    {
      "epoch": 0.003429355281207133,
      "eval_loss": 3.6764440536499023,
      "eval_runtime": 206.3223,
      "eval_samples_per_second": 11.904,
      "eval_steps_per_second": 5.952,
      "step": 20
    },
    {
      "epoch": 0.00360082304526749,
      "grad_norm": 67.11266326904297,
      "learning_rate": 3.308693936411421e-05,
      "loss": 12.8917,
      "step": 21
    },
    {
      "epoch": 0.0037722908093278463,
      "grad_norm": 72.69898223876953,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 13.5694,
      "step": 22
    },
    {
      "epoch": 0.003943758573388203,
      "grad_norm": 55.905399322509766,
      "learning_rate": 8.645454235739903e-06,
      "loss": 15.623,
      "step": 23
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 71.50740814208984,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 12.5749,
      "step": 24
    },
    {
      "epoch": 0.0042866941015089165,
      "grad_norm": 76.84934997558594,
      "learning_rate": 0.0,
      "loss": 15.4344,
      "step": 25
    },
    {
      "epoch": 0.0042866941015089165,
      "eval_loss": 3.657539129257202,
      "eval_runtime": 206.8471,
      "eval_samples_per_second": 11.874,
      "eval_steps_per_second": 5.937,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 219321414451200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}