{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.21551724137931033,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004310344827586207,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.004310344827586207,
      "eval_loss": NaN,
      "eval_runtime": 2.1475,
      "eval_samples_per_second": 23.283,
      "eval_steps_per_second": 6.054,
      "step": 1
    },
    {
      "epoch": 0.008620689655172414,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.01293103448275862,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.017241379310344827,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.021551724137931036,
      "grad_norm": NaN,
      "learning_rate": 9.997590643643647e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.02586206896551724,
      "grad_norm": NaN,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.03017241379310345,
      "grad_norm": NaN,
      "learning_rate": 9.978331270024886e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.034482758620689655,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.03879310344827586,
      "grad_norm": NaN,
      "learning_rate": 9.939894994381957e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.04310344827586207,
      "grad_norm": NaN,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.04741379310344827,
      "grad_norm": NaN,
      "learning_rate": 9.882446406748002e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.05603448275862069,
      "grad_norm": NaN,
      "learning_rate": 9.80623151079494e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0603448275862069,
      "grad_norm": NaN,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.06465517241379311,
      "grad_norm": NaN,
      "learning_rate": 9.711576670407965e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.07327586206896551,
      "grad_norm": NaN,
      "learning_rate": 9.598887212145291e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.07758620689655173,
      "grad_norm": NaN,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.08189655172413793,
      "grad_norm": NaN,
      "learning_rate": 9.468645689567598e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.09051724137931035,
      "grad_norm": NaN,
      "learning_rate": 9.321409816869605e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.09482758620689655,
      "grad_norm": NaN,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.09913793103448276,
      "grad_norm": NaN,
      "learning_rate": 9.157810080662269e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.10775862068965517,
      "grad_norm": NaN,
      "learning_rate": 8.978547040132317e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.10775862068965517,
      "eval_loss": NaN,
      "eval_runtime": 1.3983,
      "eval_samples_per_second": 35.756,
      "eval_steps_per_second": 9.297,
      "step": 25
    },
    {
      "epoch": 0.11206896551724138,
      "grad_norm": NaN,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.11637931034482758,
      "grad_norm": NaN,
      "learning_rate": 8.78438832714026e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1206896551724138,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.125,
      "grad_norm": NaN,
      "learning_rate": 8.57616535910292e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": NaN,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.1336206896551724,
      "grad_norm": NaN,
      "learning_rate": 8.354769778736406e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.14224137931034483,
      "grad_norm": NaN,
      "learning_rate": 8.12114963590511e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.14655172413793102,
      "grad_norm": NaN,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.15086206896551724,
      "grad_norm": NaN,
      "learning_rate": 7.876305327926657e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.15517241379310345,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.15948275862068967,
      "grad_norm": NaN,
      "learning_rate": 7.62128531571699e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.16379310344827586,
      "grad_norm": NaN,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.16810344827586207,
      "grad_norm": NaN,
      "learning_rate": 7.357181634119777e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.17672413793103448,
      "grad_norm": NaN,
      "learning_rate": 7.085125215645552e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.1810344827586207,
      "grad_norm": NaN,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.1853448275862069,
      "grad_norm": NaN,
      "learning_rate": 6.80628104764508e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.1896551724137931,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.1939655172413793,
      "grad_norm": NaN,
      "learning_rate": 6.52184318365468e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.19827586206896552,
      "grad_norm": NaN,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.2025862068965517,
      "grad_norm": NaN,
      "learning_rate": 6.23302963027565e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.21120689655172414,
      "grad_norm": NaN,
      "learning_rate": 5.941077131483025e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": NaN,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.21551724137931033,
      "eval_loss": NaN,
      "eval_runtime": 1.3982,
      "eval_samples_per_second": 35.76,
      "eval_steps_per_second": 9.297,
      "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": 5.6275728548338074e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}