{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05261600184156007,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010523200368312013,
      "grad_norm": 0.4822825789451599,
      "learning_rate": 2e-05,
      "loss": 2.4474,
      "step": 1
    },
    {
      "epoch": 0.0010523200368312013,
      "eval_loss": NaN,
      "eval_runtime": 2.9982,
      "eval_samples_per_second": 16.677,
      "eval_steps_per_second": 4.336,
      "step": 1
    },
    {
      "epoch": 0.0021046400736624026,
      "grad_norm": 0.5478483438491821,
      "learning_rate": 4e-05,
      "loss": 2.5343,
      "step": 2
    },
    {
      "epoch": 0.0031569601104936037,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 141060.9688,
      "step": 3
    },
    {
      "epoch": 0.004209280147324805,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.005261600184156006,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0063139202209872075,
      "grad_norm": NaN,
      "learning_rate": 9.997539658034168e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0073662402578184094,
      "grad_norm": NaN,
      "learning_rate": 9.990161322484486e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00841856029464961,
      "grad_norm": NaN,
      "learning_rate": 9.977873061452552e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00947088033148081,
      "grad_norm": NaN,
      "learning_rate": 9.96068831197139e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010523200368312013,
      "grad_norm": NaN,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.011575520405143215,
      "grad_norm": NaN,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.012627840441974415,
      "grad_norm": NaN,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.013680160478805617,
      "grad_norm": NaN,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.014732480515636819,
      "grad_norm": NaN,
      "learning_rate": 9.80216101690461e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.01578480055246802,
      "grad_norm": NaN,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.01683712058929922,
      "grad_norm": NaN,
      "learning_rate": 9.705540090697575e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.01788944062613042,
      "grad_norm": NaN,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.01894176066296162,
      "grad_norm": NaN,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.019994080699792825,
      "grad_norm": NaN,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.021046400736624025,
      "grad_norm": NaN,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.022098720773455226,
      "grad_norm": NaN,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.02315104081028643,
      "grad_norm": NaN,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.02420336084711763,
      "grad_norm": NaN,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.02525568088394883,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.026308000920780034,
      "grad_norm": NaN,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.026308000920780034,
      "eval_loss": NaN,
      "eval_runtime": 1.4983,
      "eval_samples_per_second": 33.371,
      "eval_steps_per_second": 8.676,
      "step": 25
    },
    {
      "epoch": 0.027360320957611234,
      "grad_norm": NaN,
      "learning_rate": 8.957804998855866e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.028412640994442434,
      "grad_norm": NaN,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.029464961031273638,
      "grad_norm": NaN,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.030517281068104838,
      "grad_norm": NaN,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.03156960110493604,
      "grad_norm": NaN,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03262192114176724,
      "grad_norm": NaN,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.03367424117859844,
      "grad_norm": NaN,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.03472656121542964,
      "grad_norm": NaN,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.03577888125226084,
      "grad_norm": NaN,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.03683120128909204,
      "grad_norm": NaN,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.03788352132592324,
      "grad_norm": NaN,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.03893584136275445,
      "grad_norm": NaN,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.03998816139958565,
      "grad_norm": NaN,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.04104048143641685,
      "grad_norm": NaN,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.04209280147324805,
      "grad_norm": NaN,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04314512151007925,
      "grad_norm": NaN,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.04419744154691045,
      "grad_norm": NaN,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.04524976158374166,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.04630208162057286,
      "grad_norm": NaN,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.04735440165740406,
      "grad_norm": NaN,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04840672169423526,
      "grad_norm": NaN,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.04945904173106646,
      "grad_norm": NaN,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.05051136176789766,
      "grad_norm": NaN,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.05156368180472886,
      "grad_norm": NaN,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.05261600184156007,
      "grad_norm": NaN,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.05261600184156007,
      "eval_loss": NaN,
      "eval_runtime": 3.304,
      "eval_samples_per_second": 15.133,
      "eval_steps_per_second": 3.935,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.305284264198144e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}