{
  "best_metric": 1.1993739604949951,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.006404560046753288,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025618240187013155,
      "grad_norm": 1.0117958784103394,
      "learning_rate": 5e-05,
      "loss": 2.8953,
      "step": 1
    },
    {
      "epoch": 0.00025618240187013155,
      "eval_loss": 3.3035411834716797,
      "eval_runtime": 1.3216,
      "eval_samples_per_second": 37.834,
      "eval_steps_per_second": 9.837,
      "step": 1
    },
    {
      "epoch": 0.0005123648037402631,
      "grad_norm": 3.5799102783203125,
      "learning_rate": 0.0001,
      "loss": 2.9788,
      "step": 2
    },
    {
      "epoch": 0.0007685472056103946,
      "grad_norm": 2.472435474395752,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.9668,
      "step": 3
    },
    {
      "epoch": 0.0010247296074805262,
      "grad_norm": 2.5880753993988037,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.7071,
      "step": 4
    },
    {
      "epoch": 0.0012809120093506578,
      "grad_norm": 3.2060391902923584,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.4239,
      "step": 5
    },
    {
      "epoch": 0.001537094411220789,
      "grad_norm": 2.78033447265625,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.2182,
      "step": 6
    },
    {
      "epoch": 0.0017932768130909207,
      "grad_norm": 3.5117530822753906,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.9991,
      "step": 7
    },
    {
      "epoch": 0.0020494592149610524,
      "grad_norm": 49.99619674682617,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.158,
      "step": 8
    },
    {
      "epoch": 0.002305641616831184,
      "grad_norm": 14.32833194732666,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.781,
      "step": 9
    },
    {
      "epoch": 0.0025618240187013155,
      "grad_norm": 5.2996296882629395,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.5104,
      "step": 10
    },
    {
      "epoch": 0.0028180064205714467,
      "grad_norm": 4.237436771392822,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.3103,
      "step": 11
    },
    {
      "epoch": 0.003074188822441578,
      "grad_norm": 3.8762218952178955,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.1729,
      "step": 12
    },
    {
      "epoch": 0.0033303712243117098,
      "grad_norm": 1.1300048828125,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.6434,
      "step": 13
    },
    {
      "epoch": 0.0035865536261818413,
      "grad_norm": 2.842411994934082,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.3702,
      "step": 14
    },
    {
      "epoch": 0.003842736028051973,
      "grad_norm": 1.7373723983764648,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.0943,
      "step": 15
    },
    {
      "epoch": 0.004098918429922105,
      "grad_norm": 1.6425620317459106,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.6383,
      "step": 16
    },
    {
      "epoch": 0.004355100831792236,
      "grad_norm": 1.6332066059112549,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.3914,
      "step": 17
    },
    {
      "epoch": 0.004611283233662368,
      "grad_norm": 1.2231783866882324,
      "learning_rate": 7.75e-05,
      "loss": 1.3286,
      "step": 18
    },
    {
      "epoch": 0.0048674656355324995,
      "grad_norm": 1.177355170249939,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.1223,
      "step": 19
    },
    {
      "epoch": 0.005123648037402631,
      "grad_norm": 1.1488226652145386,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.0321,
      "step": 20
    },
    {
      "epoch": 0.005379830439272763,
      "grad_norm": 0.7047779560089111,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.9133,
      "step": 21
    },
    {
      "epoch": 0.005636012841142893,
      "grad_norm": 0.6960715055465698,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.8929,
      "step": 22
    },
    {
      "epoch": 0.005892195243013025,
      "grad_norm": 0.8420125246047974,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.818,
      "step": 23
    },
    {
      "epoch": 0.006148377644883156,
      "grad_norm": 1.9466040134429932,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.9685,
      "step": 24
    },
    {
      "epoch": 0.006404560046753288,
      "grad_norm": 1.9700946807861328,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.0097,
      "step": 25
    },
    {
      "epoch": 0.006404560046753288,
      "eval_loss": 1.1993739604949951,
      "eval_runtime": 1.3174,
      "eval_samples_per_second": 37.954,
      "eval_steps_per_second": 9.868,
      "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": 1.47650456322048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}