{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.00421887524785892,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437750495717842e-05,
      "grad_norm": NaN,
      "learning_rate": 1.004e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.437750495717842e-05,
      "eval_loss": NaN,
      "eval_runtime": 971.3872,
      "eval_samples_per_second": 5.137,
      "eval_steps_per_second": 1.285,
      "step": 1
    },
    {
      "epoch": 0.00016875500991435683,
      "grad_norm": NaN,
      "learning_rate": 2.008e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00025313251487153526,
      "grad_norm": NaN,
      "learning_rate": 3.012e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00033751001982871366,
      "grad_norm": NaN,
      "learning_rate": 4.016e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00042188752478589206,
      "grad_norm": NaN,
      "learning_rate": 5.02e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005062650297430705,
      "grad_norm": NaN,
      "learning_rate": 6.024e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005906425347002489,
      "grad_norm": NaN,
      "learning_rate": 7.028e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006750200396574273,
      "grad_norm": NaN,
      "learning_rate": 8.032e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0007593975446146058,
      "grad_norm": NaN,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0008437750495717841,
      "grad_norm": NaN,
      "learning_rate": 0.0001004,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0009281525545289626,
      "grad_norm": NaN,
      "learning_rate": 9.987157894736842e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.001012530059486141,
      "grad_norm": NaN,
      "learning_rate": 9.934315789473684e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0010969075644433194,
      "grad_norm": NaN,
      "learning_rate": 9.881473684210525e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0011812850694004977,
      "grad_norm": NaN,
      "learning_rate": 9.828631578947369e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0012656625743576763,
      "grad_norm": NaN,
      "learning_rate": 9.77578947368421e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0013500400793148546,
      "grad_norm": NaN,
      "learning_rate": 9.722947368421052e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.001434417584272033,
      "grad_norm": NaN,
      "learning_rate": 9.670105263157895e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0015187950892292116,
      "grad_norm": NaN,
      "learning_rate": 9.617263157894737e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00160317259418639,
      "grad_norm": NaN,
      "learning_rate": 9.564421052631579e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0016875500991435683,
      "grad_norm": NaN,
      "learning_rate": 9.511578947368421e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0017719276041007468,
      "grad_norm": NaN,
      "learning_rate": 9.458736842105264e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0018563051090579252,
      "grad_norm": NaN,
      "learning_rate": 9.405894736842106e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0019406826140151035,
      "grad_norm": NaN,
      "learning_rate": 9.353052631578947e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.002025060118972282,
      "grad_norm": NaN,
      "learning_rate": 9.300210526315789e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.00210943762392946,
      "grad_norm": NaN,
      "learning_rate": 9.247368421052631e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0021938151288866388,
      "grad_norm": NaN,
      "learning_rate": 9.194526315789473e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0022781926338438173,
      "grad_norm": NaN,
      "learning_rate": 9.141684210526316e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0023625701388009955,
      "grad_norm": NaN,
      "learning_rate": 9.088842105263158e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.002446947643758174,
      "grad_norm": NaN,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0025313251487153526,
      "grad_norm": NaN,
      "learning_rate": 8.983157894736843e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0026157026536725307,
      "grad_norm": NaN,
      "learning_rate": 8.930315789473684e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0027000801586297093,
      "grad_norm": NaN,
      "learning_rate": 8.877473684210526e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.002784457663586888,
      "grad_norm": NaN,
      "learning_rate": 8.824631578947368e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.002868835168544066,
      "grad_norm": NaN,
      "learning_rate": 8.771789473684211e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0029532126735012446,
      "grad_norm": NaN,
      "learning_rate": 8.718947368421053e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.003037590178458423,
      "grad_norm": NaN,
      "learning_rate": 8.666105263157895e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0031219676834156013,
      "grad_norm": NaN,
      "learning_rate": 8.613263157894737e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.00320634518837278,
      "grad_norm": NaN,
      "learning_rate": 8.560421052631578e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0032907226933299584,
      "grad_norm": NaN,
      "learning_rate": 8.50757894736842e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0033751001982871365,
      "grad_norm": NaN,
      "learning_rate": 8.454736842105263e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.003459477703244315,
      "grad_norm": NaN,
      "learning_rate": 8.401894736842106e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0035438552082014936,
      "grad_norm": NaN,
      "learning_rate": 8.349052631578948e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0036282327131586718,
      "grad_norm": NaN,
      "learning_rate": 8.29621052631579e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0037126102181158503,
      "grad_norm": NaN,
      "learning_rate": 8.243368421052632e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.003796987723073029,
      "grad_norm": NaN,
      "learning_rate": 8.190526315789474e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.003881365228030207,
      "grad_norm": NaN,
      "learning_rate": 8.137684210526315e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.003965742732987386,
      "grad_norm": NaN,
      "learning_rate": 8.084842105263157e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.004050120237944564,
      "grad_norm": NaN,
      "learning_rate": 8.032e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.004134497742901743,
      "grad_norm": NaN,
      "learning_rate": 7.979157894736842e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.00421887524785892,
      "grad_norm": NaN,
      "learning_rate": 7.926315789473684e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00421887524785892,
      "eval_loss": NaN,
      "eval_runtime": 970.4964,
      "eval_samples_per_second": 5.142,
      "eval_steps_per_second": 1.286,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 3.5412502992912384e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}