{
  "best_metric": 1.844842553138733,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.8869179600886918,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 12.724061012268066,
      "learning_rate": 5e-05,
      "loss": 4.6763,
      "step": 1
    },
    {
      "epoch": 0.03547671840354767,
      "eval_loss": 5.99407958984375,
      "eval_runtime": 0.8254,
      "eval_samples_per_second": 60.573,
      "eval_steps_per_second": 15.749,
      "step": 1
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 14.900910377502441,
      "learning_rate": 0.0001,
      "loss": 5.43,
      "step": 2
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 12.636441230773926,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.617,
      "step": 3
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 7.304109573364258,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.1331,
      "step": 4
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 9.609624862670898,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.7081,
      "step": 5
    },
    {
      "epoch": 0.21286031042128603,
      "grad_norm": 7.860935688018799,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.7118,
      "step": 6
    },
    {
      "epoch": 0.24833702882483372,
      "grad_norm": 4.936010360717773,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.396,
      "step": 7
    },
    {
      "epoch": 0.2838137472283814,
      "grad_norm": 10.622501373291016,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.3273,
      "step": 8
    },
    {
      "epoch": 0.31929046563192903,
      "grad_norm": 10.488219261169434,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.3307,
      "step": 9
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 3.8527562618255615,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0453,
      "step": 10
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 6.716139793395996,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.1969,
      "step": 11
    },
    {
      "epoch": 0.42572062084257206,
      "grad_norm": 6.578034400939941,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.8983,
      "step": 12
    },
    {
      "epoch": 0.4611973392461197,
      "grad_norm": 3.6023688316345215,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.8527,
      "step": 13
    },
    {
      "epoch": 0.49667405764966743,
      "grad_norm": 2.803765296936035,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.9696,
      "step": 14
    },
    {
      "epoch": 0.532150776053215,
      "grad_norm": 2.6298434734344482,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.8644,
      "step": 15
    },
    {
      "epoch": 0.5676274944567627,
      "grad_norm": 2.5654900074005127,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.9544,
      "step": 16
    },
    {
      "epoch": 0.6031042128603105,
      "grad_norm": 2.001566171646118,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.8754,
      "step": 17
    },
    {
      "epoch": 0.6385809312638581,
      "grad_norm": 2.398838520050049,
      "learning_rate": 7.75e-05,
      "loss": 1.9237,
      "step": 18
    },
    {
      "epoch": 0.6740576496674058,
      "grad_norm": 2.143735885620117,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.7714,
      "step": 19
    },
    {
      "epoch": 0.7095343680709535,
      "grad_norm": 1.954122543334961,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.7033,
      "step": 20
    },
    {
      "epoch": 0.7450110864745011,
      "grad_norm": 2.0909314155578613,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.7329,
      "step": 21
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 1.8812015056610107,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.713,
      "step": 22
    },
    {
      "epoch": 0.8159645232815964,
      "grad_norm": 1.8215457201004028,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.8447,
      "step": 23
    },
    {
      "epoch": 0.8514412416851441,
      "grad_norm": 2.0654754638671875,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.8287,
      "step": 24
    },
    {
      "epoch": 0.8869179600886918,
      "grad_norm": 2.009129047393799,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.7592,
      "step": 25
    },
    {
      "epoch": 0.8869179600886918,
      "eval_loss": 1.844842553138733,
      "eval_runtime": 0.8732,
      "eval_samples_per_second": 57.26,
      "eval_steps_per_second": 14.888,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 7.94731890081792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}