{
  "best_metric": 0.22036908566951752,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.10188487009679063,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004075394803871625,
      "grad_norm": 3.6880290508270264,
      "learning_rate": 5e-05,
      "loss": 2.9145,
      "step": 1
    },
    {
      "epoch": 0.004075394803871625,
      "eval_loss": 1.8356962203979492,
      "eval_runtime": 4.8102,
      "eval_samples_per_second": 10.395,
      "eval_steps_per_second": 2.703,
      "step": 1
    },
    {
      "epoch": 0.00815078960774325,
      "grad_norm": 6.949686527252197,
      "learning_rate": 0.0001,
      "loss": 5.8006,
      "step": 2
    },
    {
      "epoch": 0.012226184411614875,
      "grad_norm": 11.85057544708252,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.9155,
      "step": 3
    },
    {
      "epoch": 0.0163015792154865,
      "grad_norm": 17.87611198425293,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.6816,
      "step": 4
    },
    {
      "epoch": 0.020376974019358125,
      "grad_norm": 24.372392654418945,
      "learning_rate": 9.913533761814537e-05,
      "loss": 14.1583,
      "step": 5
    },
    {
      "epoch": 0.02445236882322975,
      "grad_norm": 26.836442947387695,
      "learning_rate": 9.846666218300807e-05,
      "loss": 17.8215,
      "step": 6
    },
    {
      "epoch": 0.028527763627101375,
      "grad_norm": 56.37813186645508,
      "learning_rate": 9.761185582727977e-05,
      "loss": 34.1831,
      "step": 7
    },
    {
      "epoch": 0.032603158430973,
      "grad_norm": 24.23225212097168,
      "learning_rate": 9.657457896300791e-05,
      "loss": 15.4885,
      "step": 8
    },
    {
      "epoch": 0.036678553234844626,
      "grad_norm": 22.243453979492188,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.7114,
      "step": 9
    },
    {
      "epoch": 0.04075394803871625,
      "grad_norm": 22.904632568359375,
      "learning_rate": 9.397114317029975e-05,
      "loss": 8.7383,
      "step": 10
    },
    {
      "epoch": 0.044829342842587876,
      "grad_norm": 19.449880599975586,
      "learning_rate": 9.241613255361455e-05,
      "loss": 8.7931,
      "step": 11
    },
    {
      "epoch": 0.0489047376464595,
      "grad_norm": 19.61833953857422,
      "learning_rate": 9.070090031310558e-05,
      "loss": 8.3072,
      "step": 12
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 23.143583297729492,
      "learning_rate": 8.883279133655399e-05,
      "loss": 9.2176,
      "step": 13
    },
    {
      "epoch": 0.05705552725420275,
      "grad_norm": 27.774089813232422,
      "learning_rate": 8.681980515339464e-05,
      "loss": 5.8898,
      "step": 14
    },
    {
      "epoch": 0.061130922058074376,
      "grad_norm": 12.567861557006836,
      "learning_rate": 8.467056167950311e-05,
      "loss": 5.0024,
      "step": 15
    },
    {
      "epoch": 0.065206316861946,
      "grad_norm": 7.958722114562988,
      "learning_rate": 8.239426430539243e-05,
      "loss": 5.0515,
      "step": 16
    },
    {
      "epoch": 0.06928171166581763,
      "grad_norm": 8.585467338562012,
      "learning_rate": 8.000066048588211e-05,
      "loss": 5.7709,
      "step": 17
    },
    {
      "epoch": 0.07335710646968925,
      "grad_norm": 13.094317436218262,
      "learning_rate": 7.75e-05,
      "loss": 6.3559,
      "step": 18
    },
    {
      "epoch": 0.07743250127356088,
      "grad_norm": 23.679494857788086,
      "learning_rate": 7.490299105985507e-05,
      "loss": 9.2488,
      "step": 19
    },
    {
      "epoch": 0.0815078960774325,
      "grad_norm": 49.4882698059082,
      "learning_rate": 7.222075445642904e-05,
      "loss": 20.8839,
      "step": 20
    },
    {
      "epoch": 0.08558329088130413,
      "grad_norm": 10.968897819519043,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.2323,
      "step": 21
    },
    {
      "epoch": 0.08965868568517575,
      "grad_norm": 6.621339321136475,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.3759,
      "step": 22
    },
    {
      "epoch": 0.09373408048904738,
      "grad_norm": 7.691227436065674,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.23,
      "step": 23
    },
    {
      "epoch": 0.097809475292919,
      "grad_norm": 8.350950241088867,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.9104,
      "step": 24
    },
    {
      "epoch": 0.10188487009679063,
      "grad_norm": 17.605392456054688,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.5359,
      "step": 25
    },
    {
      "epoch": 0.10188487009679063,
      "eval_loss": 0.22036908566951752,
      "eval_runtime": 4.8591,
      "eval_samples_per_second": 10.29,
      "eval_steps_per_second": 2.675,
      "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": 4.1382580590739456e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}