{
  "best_metric": 0.622530996799469,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.4925373134328357,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 3.4969444274902344,
      "learning_rate": 5e-05,
      "loss": 4.0203,
      "step": 1
    },
    {
      "epoch": 0.05970149253731343,
      "eval_loss": 4.0696187019348145,
      "eval_runtime": 1.4729,
      "eval_samples_per_second": 33.947,
      "eval_steps_per_second": 8.826,
      "step": 1
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 3.6559250354766846,
      "learning_rate": 0.0001,
      "loss": 4.0385,
      "step": 2
    },
    {
      "epoch": 0.1791044776119403,
      "grad_norm": 3.5034873485565186,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.9289,
      "step": 3
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 3.403470754623413,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 2.9451396465301514,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.9146,
      "step": 5
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 3.2620737552642822,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.5116,
      "step": 6
    },
    {
      "epoch": 0.417910447761194,
      "grad_norm": 3.4186899662017822,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.1342,
      "step": 7
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 3.5180110931396484,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.7708,
      "step": 8
    },
    {
      "epoch": 0.5373134328358209,
      "grad_norm": 3.15236234664917,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.5748,
      "step": 9
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 2.916743278503418,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.3533,
      "step": 10
    },
    {
      "epoch": 0.6567164179104478,
      "grad_norm": 2.617918014526367,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.0945,
      "step": 11
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 2.6230955123901367,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.0196,
      "step": 12
    },
    {
      "epoch": 0.7761194029850746,
      "grad_norm": 2.837193012237549,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.0562,
      "step": 13
    },
    {
      "epoch": 0.835820895522388,
      "grad_norm": 2.3078386783599854,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.9869,
      "step": 14
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 2.06661057472229,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.8797,
      "step": 15
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 2.422396421432495,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.8551,
      "step": 16
    },
    {
      "epoch": 1.0149253731343284,
      "grad_norm": 2.36983585357666,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.0677,
      "step": 17
    },
    {
      "epoch": 1.0746268656716418,
      "grad_norm": 1.9366710186004639,
      "learning_rate": 7.75e-05,
      "loss": 0.8165,
      "step": 18
    },
    {
      "epoch": 1.1343283582089552,
      "grad_norm": 1.3156859874725342,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.7562,
      "step": 19
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 1.8956644535064697,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.7083,
      "step": 20
    },
    {
      "epoch": 1.2537313432835822,
      "grad_norm": 1.5644067525863647,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.7084,
      "step": 21
    },
    {
      "epoch": 1.3134328358208955,
      "grad_norm": 1.1243278980255127,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.6813,
      "step": 22
    },
    {
      "epoch": 1.373134328358209,
      "grad_norm": 0.9743745923042297,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.6329,
      "step": 23
    },
    {
      "epoch": 1.4328358208955223,
      "grad_norm": 1.0701549053192139,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.6253,
      "step": 24
    },
    {
      "epoch": 1.4925373134328357,
      "grad_norm": 1.0772173404693604,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.6433,
      "step": 25
    },
    {
      "epoch": 1.4925373134328357,
      "eval_loss": 0.622530996799469,
      "eval_runtime": 0.9645,
      "eval_samples_per_second": 51.839,
      "eval_steps_per_second": 13.478,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3.91521434075136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}