{
  "best_metric": 131.32179260253906,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.009234676209165417,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004617338104582708,
      "grad_norm": 3681.328369140625,
      "learning_rate": 2e-05,
      "loss": 541.1149,
      "step": 1
    },
    {
      "epoch": 0.0004617338104582708,
      "eval_loss": 132.59771728515625,
      "eval_runtime": 30.8528,
      "eval_samples_per_second": 29.56,
      "eval_steps_per_second": 14.78,
      "step": 1
    },
    {
      "epoch": 0.0009234676209165416,
      "grad_norm": 4573.46484375,
      "learning_rate": 4e-05,
      "loss": 622.8275,
      "step": 2
    },
    {
      "epoch": 0.0013852014313748124,
      "grad_norm": 2545.527587890625,
      "learning_rate": 6e-05,
      "loss": 541.8585,
      "step": 3
    },
    {
      "epoch": 0.0018469352418330831,
      "grad_norm": 4183.0849609375,
      "learning_rate": 8e-05,
      "loss": 591.893,
      "step": 4
    },
    {
      "epoch": 0.002308669052291354,
      "grad_norm": 1909.5782470703125,
      "learning_rate": 0.0001,
      "loss": 483.765,
      "step": 5
    },
    {
      "epoch": 0.002308669052291354,
      "eval_loss": 132.56350708007812,
      "eval_runtime": 30.8124,
      "eval_samples_per_second": 29.598,
      "eval_steps_per_second": 14.799,
      "step": 5
    },
    {
      "epoch": 0.0027704028627496247,
      "grad_norm": 2903.951171875,
      "learning_rate": 0.00012,
      "loss": 624.7967,
      "step": 6
    },
    {
      "epoch": 0.0032321366732078957,
      "grad_norm": 3412.83447265625,
      "learning_rate": 0.00014,
      "loss": 570.1699,
      "step": 7
    },
    {
      "epoch": 0.0036938704836661663,
      "grad_norm": 3161.602783203125,
      "learning_rate": 0.00016,
      "loss": 491.8676,
      "step": 8
    },
    {
      "epoch": 0.004155604294124437,
      "grad_norm": 6774.43505859375,
      "learning_rate": 0.00018,
      "loss": 511.9115,
      "step": 9
    },
    {
      "epoch": 0.004617338104582708,
      "grad_norm": 5741.693359375,
      "learning_rate": 0.0002,
      "loss": 587.5868,
      "step": 10
    },
    {
      "epoch": 0.004617338104582708,
      "eval_loss": 132.2397003173828,
      "eval_runtime": 29.9143,
      "eval_samples_per_second": 30.487,
      "eval_steps_per_second": 15.244,
      "step": 10
    },
    {
      "epoch": 0.005079071915040979,
      "grad_norm": 2912.842529296875,
      "learning_rate": 0.00019781476007338058,
      "loss": 551.7598,
      "step": 11
    },
    {
      "epoch": 0.005540805725499249,
      "grad_norm": 4430.501953125,
      "learning_rate": 0.0001913545457642601,
      "loss": 481.611,
      "step": 12
    },
    {
      "epoch": 0.006002539535957521,
      "grad_norm": 2456.33056640625,
      "learning_rate": 0.00018090169943749476,
      "loss": 485.4459,
      "step": 13
    },
    {
      "epoch": 0.006464273346415791,
      "grad_norm": 2646.41943359375,
      "learning_rate": 0.00016691306063588583,
      "loss": 510.7367,
      "step": 14
    },
    {
      "epoch": 0.006926007156874062,
      "grad_norm": 1958.2275390625,
      "learning_rate": 0.00015000000000000001,
      "loss": 421.8189,
      "step": 15
    },
    {
      "epoch": 0.006926007156874062,
      "eval_loss": 131.59474182128906,
      "eval_runtime": 30.1256,
      "eval_samples_per_second": 30.273,
      "eval_steps_per_second": 15.137,
      "step": 15
    },
    {
      "epoch": 0.007387740967332333,
      "grad_norm": 9255.2744140625,
      "learning_rate": 0.00013090169943749476,
      "loss": 589.606,
      "step": 16
    },
    {
      "epoch": 0.007849474777790603,
      "grad_norm": 3850.311767578125,
      "learning_rate": 0.00011045284632676536,
      "loss": 495.3413,
      "step": 17
    },
    {
      "epoch": 0.008311208588248874,
      "grad_norm": 4440.9609375,
      "learning_rate": 8.954715367323468e-05,
      "loss": 520.9756,
      "step": 18
    },
    {
      "epoch": 0.008772942398707146,
      "grad_norm": 4155.97265625,
      "learning_rate": 6.909830056250527e-05,
      "loss": 580.1696,
      "step": 19
    },
    {
      "epoch": 0.009234676209165417,
      "grad_norm": 2721.349365234375,
      "learning_rate": 5.000000000000002e-05,
      "loss": 462.3867,
      "step": 20
    },
    {
      "epoch": 0.009234676209165417,
      "eval_loss": 131.32179260253906,
      "eval_runtime": 29.506,
      "eval_samples_per_second": 30.909,
      "eval_steps_per_second": 15.454,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 22149951651840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}