{
  "best_metric": 3.1054515838623047,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01160631383472609,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00046425255338904364,
      "grad_norm": 106.3442153930664,
      "learning_rate": 2e-05,
      "loss": 18.8198,
      "step": 1
    },
    {
      "epoch": 0.00046425255338904364,
      "eval_loss": 4.078410625457764,
      "eval_runtime": 57.5601,
      "eval_samples_per_second": 15.757,
      "eval_steps_per_second": 7.887,
      "step": 1
    },
    {
      "epoch": 0.0009285051067780873,
      "grad_norm": 113.46746826171875,
      "learning_rate": 4e-05,
      "loss": 17.7549,
      "step": 2
    },
    {
      "epoch": 0.001392757660167131,
      "grad_norm": 116.7121810913086,
      "learning_rate": 6e-05,
      "loss": 17.8524,
      "step": 3
    },
    {
      "epoch": 0.0018570102135561746,
      "grad_norm": 101.75821685791016,
      "learning_rate": 8e-05,
      "loss": 18.4793,
      "step": 4
    },
    {
      "epoch": 0.002321262766945218,
      "grad_norm": 114.62692260742188,
      "learning_rate": 0.0001,
      "loss": 19.6564,
      "step": 5
    },
    {
      "epoch": 0.002321262766945218,
      "eval_loss": 3.9964888095855713,
      "eval_runtime": 54.6787,
      "eval_samples_per_second": 16.588,
      "eval_steps_per_second": 8.303,
      "step": 5
    },
    {
      "epoch": 0.002785515320334262,
      "grad_norm": 103.60193634033203,
      "learning_rate": 0.00012,
      "loss": 14.7416,
      "step": 6
    },
    {
      "epoch": 0.0032497678737233053,
      "grad_norm": 98.48835754394531,
      "learning_rate": 0.00014,
      "loss": 16.4261,
      "step": 7
    },
    {
      "epoch": 0.003714020427112349,
      "grad_norm": 94.48746490478516,
      "learning_rate": 0.00016,
      "loss": 15.1889,
      "step": 8
    },
    {
      "epoch": 0.004178272980501393,
      "grad_norm": 87.05733489990234,
      "learning_rate": 0.00018,
      "loss": 15.0919,
      "step": 9
    },
    {
      "epoch": 0.004642525533890436,
      "grad_norm": 91.75668334960938,
      "learning_rate": 0.0002,
      "loss": 15.9394,
      "step": 10
    },
    {
      "epoch": 0.004642525533890436,
      "eval_loss": 3.6218421459198,
      "eval_runtime": 54.664,
      "eval_samples_per_second": 16.592,
      "eval_steps_per_second": 8.305,
      "step": 10
    },
    {
      "epoch": 0.00510677808727948,
      "grad_norm": 92.22998046875,
      "learning_rate": 0.00019781476007338058,
      "loss": 14.8228,
      "step": 11
    },
    {
      "epoch": 0.005571030640668524,
      "grad_norm": 70.96794128417969,
      "learning_rate": 0.0001913545457642601,
      "loss": 14.6588,
      "step": 12
    },
    {
      "epoch": 0.0060352831940575676,
      "grad_norm": 119.14212799072266,
      "learning_rate": 0.00018090169943749476,
      "loss": 14.8817,
      "step": 13
    },
    {
      "epoch": 0.0064995357474466105,
      "grad_norm": 91.25348663330078,
      "learning_rate": 0.00016691306063588583,
      "loss": 12.9302,
      "step": 14
    },
    {
      "epoch": 0.006963788300835654,
      "grad_norm": 98.52769470214844,
      "learning_rate": 0.00015000000000000001,
      "loss": 11.984,
      "step": 15
    },
    {
      "epoch": 0.006963788300835654,
      "eval_loss": 3.26326584815979,
      "eval_runtime": 53.6764,
      "eval_samples_per_second": 16.898,
      "eval_steps_per_second": 8.458,
      "step": 15
    },
    {
      "epoch": 0.007428040854224698,
      "grad_norm": 99.44156646728516,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.8699,
      "step": 16
    },
    {
      "epoch": 0.007892293407613741,
      "grad_norm": 103.4403076171875,
      "learning_rate": 0.00011045284632676536,
      "loss": 12.4075,
      "step": 17
    },
    {
      "epoch": 0.008356545961002786,
      "grad_norm": 156.34823608398438,
      "learning_rate": 8.954715367323468e-05,
      "loss": 11.5994,
      "step": 18
    },
    {
      "epoch": 0.008820798514391829,
      "grad_norm": 117.01519012451172,
      "learning_rate": 6.909830056250527e-05,
      "loss": 12.1546,
      "step": 19
    },
    {
      "epoch": 0.009285051067780872,
      "grad_norm": 113.8475112915039,
      "learning_rate": 5.000000000000002e-05,
      "loss": 12.0012,
      "step": 20
    },
    {
      "epoch": 0.009285051067780872,
      "eval_loss": 3.130841016769409,
      "eval_runtime": 55.1152,
      "eval_samples_per_second": 16.456,
      "eval_steps_per_second": 8.237,
      "step": 20
    },
    {
      "epoch": 0.009749303621169917,
      "grad_norm": 93.6298828125,
      "learning_rate": 3.308693936411421e-05,
      "loss": 12.52,
      "step": 21
    },
    {
      "epoch": 0.01021355617455896,
      "grad_norm": 96.63572692871094,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 10.3928,
      "step": 22
    },
    {
      "epoch": 0.010677808727948004,
      "grad_norm": 145.1343536376953,
      "learning_rate": 8.645454235739903e-06,
      "loss": 12.7345,
      "step": 23
    },
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 113.03942108154297,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 11.8607,
      "step": 24
    },
    {
      "epoch": 0.01160631383472609,
      "grad_norm": 97.68357849121094,
      "learning_rate": 0.0,
      "loss": 11.6635,
      "step": 25
    },
    {
      "epoch": 0.01160631383472609,
      "eval_loss": 3.1054515838623047,
      "eval_runtime": 55.0843,
      "eval_samples_per_second": 16.466,
      "eval_steps_per_second": 8.242,
      "step": 25
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 219321414451200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}