{
  "best_metric": 0.30715107917785645,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.055282979752608666,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022113191901043465,
      "grad_norm": 1266.8173828125,
      "learning_rate": 5e-05,
      "loss": 130.6273,
      "step": 1
    },
    {
      "epoch": 0.0022113191901043465,
      "eval_loss": 3.3367362022399902,
      "eval_runtime": 3.0918,
      "eval_samples_per_second": 16.172,
      "eval_steps_per_second": 4.205,
      "step": 1
    },
    {
      "epoch": 0.004422638380208693,
      "grad_norm": 1228.9942626953125,
      "learning_rate": 0.0001,
      "loss": 135.8005,
      "step": 2
    },
    {
      "epoch": 0.00663395757031304,
      "grad_norm": 893.6980590820312,
      "learning_rate": 9.990365154573717e-05,
      "loss": 81.7229,
      "step": 3
    },
    {
      "epoch": 0.008845276760417386,
      "grad_norm": 616.2275390625,
      "learning_rate": 9.961501876182148e-05,
      "loss": 50.632,
      "step": 4
    },
    {
      "epoch": 0.011056595950521733,
      "grad_norm": 1459.5819091796875,
      "learning_rate": 9.913533761814537e-05,
      "loss": 75.3263,
      "step": 5
    },
    {
      "epoch": 0.01326791514062608,
      "grad_norm": 315.1625671386719,
      "learning_rate": 9.846666218300807e-05,
      "loss": 21.8838,
      "step": 6
    },
    {
      "epoch": 0.015479234330730427,
      "grad_norm": 1401.111083984375,
      "learning_rate": 9.761185582727977e-05,
      "loss": 39.3447,
      "step": 7
    },
    {
      "epoch": 0.017690553520834772,
      "grad_norm": 298.81280517578125,
      "learning_rate": 9.657457896300791e-05,
      "loss": 19.4309,
      "step": 8
    },
    {
      "epoch": 0.01990187271093912,
      "grad_norm": 422.7381591796875,
      "learning_rate": 9.535927336897098e-05,
      "loss": 22.1325,
      "step": 9
    },
    {
      "epoch": 0.022113191901043466,
      "grad_norm": 443.7731628417969,
      "learning_rate": 9.397114317029975e-05,
      "loss": 19.4608,
      "step": 10
    },
    {
      "epoch": 0.02432451109114781,
      "grad_norm": 230.34886169433594,
      "learning_rate": 9.241613255361455e-05,
      "loss": 14.7356,
      "step": 11
    },
    {
      "epoch": 0.02653583028125216,
      "grad_norm": 370.49786376953125,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.2922,
      "step": 12
    },
    {
      "epoch": 0.028747149471356506,
      "grad_norm": 249.0677947998047,
      "learning_rate": 8.883279133655399e-05,
      "loss": 13.2127,
      "step": 13
    },
    {
      "epoch": 0.030958468661460854,
      "grad_norm": 180.40122985839844,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.3355,
      "step": 14
    },
    {
      "epoch": 0.0331697878515652,
      "grad_norm": 233.73875427246094,
      "learning_rate": 8.467056167950311e-05,
      "loss": 12.585,
      "step": 15
    },
    {
      "epoch": 0.035381107041669545,
      "grad_norm": 191.15699768066406,
      "learning_rate": 8.239426430539243e-05,
      "loss": 13.1807,
      "step": 16
    },
    {
      "epoch": 0.03759242623177389,
      "grad_norm": 191.31100463867188,
      "learning_rate": 8.000066048588211e-05,
      "loss": 14.3639,
      "step": 17
    },
    {
      "epoch": 0.03980374542187824,
      "grad_norm": 175.0061798095703,
      "learning_rate": 7.75e-05,
      "loss": 11.2044,
      "step": 18
    },
    {
      "epoch": 0.04201506461198259,
      "grad_norm": 147.7163848876953,
      "learning_rate": 7.490299105985507e-05,
      "loss": 12.4057,
      "step": 19
    },
    {
      "epoch": 0.04422638380208693,
      "grad_norm": 163.385009765625,
      "learning_rate": 7.222075445642904e-05,
      "loss": 9.6362,
      "step": 20
    },
    {
      "epoch": 0.04643770299219128,
      "grad_norm": 140.2444610595703,
      "learning_rate": 6.946477593864228e-05,
      "loss": 7.4195,
      "step": 21
    },
    {
      "epoch": 0.04864902218229562,
      "grad_norm": 136.61859130859375,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.4054,
      "step": 22
    },
    {
      "epoch": 0.050860341372399975,
      "grad_norm": 157.8791961669922,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.6133,
      "step": 23
    },
    {
      "epoch": 0.05307166056250432,
      "grad_norm": 169.0653839111328,
      "learning_rate": 6.087367864990233e-05,
      "loss": 9.754,
      "step": 24
    },
    {
      "epoch": 0.055282979752608666,
      "grad_norm": 191.57464599609375,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.1938,
      "step": 25
    },
    {
      "epoch": 0.055282979752608666,
      "eval_loss": 0.30715107917785645,
      "eval_runtime": 3.0653,
      "eval_samples_per_second": 16.312,
      "eval_steps_per_second": 4.241,
      "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": 2.829013890367488e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}