{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.03288391976323578,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013153567905294311,
      "grad_norm": 4.305715084075928,
      "learning_rate": 5e-05,
      "loss": 4.4764,
      "step": 1
    },
    {
      "epoch": 0.0013153567905294311,
      "eval_loss": NaN,
      "eval_runtime": 154.6996,
      "eval_samples_per_second": 33.109,
      "eval_steps_per_second": 4.144,
      "step": 1
    },
    {
      "epoch": 0.0026307135810588623,
      "grad_norm": 4.98206901550293,
      "learning_rate": 0.0001,
      "loss": 4.8066,
      "step": 2
    },
    {
      "epoch": 0.003946070371588293,
      "grad_norm": 4.7236738204956055,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.712,
      "step": 3
    },
    {
      "epoch": 0.005261427162117725,
      "grad_norm": 5.148580074310303,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.9262,
      "step": 4
    },
    {
      "epoch": 0.006576783952647156,
      "grad_norm": 6.657264232635498,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.3766,
      "step": 5
    },
    {
      "epoch": 0.007892140743176587,
      "grad_norm": 3.452958345413208,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.9662,
      "step": 6
    },
    {
      "epoch": 0.009207497533706017,
      "grad_norm": 3.356189489364624,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.5367,
      "step": 7
    },
    {
      "epoch": 0.01052285432423545,
      "grad_norm": 2.3280153274536133,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.478,
      "step": 8
    },
    {
      "epoch": 0.01183821111476488,
      "grad_norm": 2.648228406906128,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.4201,
      "step": 9
    },
    {
      "epoch": 0.013153567905294311,
      "grad_norm": 5.471138954162598,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3108,
      "step": 10
    },
    {
      "epoch": 0.014468924695823742,
      "grad_norm": 2.8087058067321777,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.0655,
      "step": 11
    },
    {
      "epoch": 0.015784281486353174,
      "grad_norm": 7.201243877410889,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.0358,
      "step": 12
    },
    {
      "epoch": 0.017099638276882604,
      "grad_norm": 3.615448236465454,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.5537,
      "step": 13
    },
    {
      "epoch": 0.018414995067412034,
      "grad_norm": 4.010716438293457,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.806,
      "step": 14
    },
    {
      "epoch": 0.019730351857941468,
      "grad_norm": 2.0730106830596924,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.6445,
      "step": 15
    },
    {
      "epoch": 0.0210457086484709,
      "grad_norm": 1.6707302331924438,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.4386,
      "step": 16
    },
    {
      "epoch": 0.02236106543900033,
      "grad_norm": 1.6326355934143066,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.3879,
      "step": 17
    },
    {
      "epoch": 0.02367642222952976,
      "grad_norm": 1.5959230661392212,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3075,
      "step": 18
    },
    {
      "epoch": 0.024991779020059193,
      "grad_norm": 1.9072798490524292,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.3008,
      "step": 19
    },
    {
      "epoch": 0.026307135810588623,
      "grad_norm": 1.344789981842041,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2003,
      "step": 20
    },
    {
      "epoch": 0.027622492601118053,
      "grad_norm": 1.4146466255187988,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.2142,
      "step": 21
    },
    {
      "epoch": 0.028937849391647483,
      "grad_norm": 1.3578002452850342,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.9889,
      "step": 22
    },
    {
      "epoch": 0.030253206182176917,
      "grad_norm": 1.4287495613098145,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.9253,
      "step": 23
    },
    {
      "epoch": 0.03156856297270635,
      "grad_norm": 1.527700424194336,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.8363,
      "step": 24
    },
    {
      "epoch": 0.03288391976323578,
      "grad_norm": 1.7608954906463623,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5056,
      "step": 25
    },
    {
      "epoch": 0.03288391976323578,
      "eval_loss": NaN,
      "eval_runtime": 154.8596,
      "eval_samples_per_second": 33.075,
      "eval_steps_per_second": 4.139,
      "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}