{
  "best_metric": 4.552499294281006,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.017114862118392058,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006845944847356823,
      "grad_norm": 1.9006248712539673,
      "learning_rate": 5e-05,
      "loss": 5.537,
      "step": 1
    },
    {
      "epoch": 0.0006845944847356823,
      "eval_loss": 5.087055683135986,
      "eval_runtime": 0.7151,
      "eval_samples_per_second": 69.917,
      "eval_steps_per_second": 18.178,
      "step": 1
    },
    {
      "epoch": 0.0013691889694713646,
      "grad_norm": 1.7246968746185303,
      "learning_rate": 0.0001,
      "loss": 5.2483,
      "step": 2
    },
    {
      "epoch": 0.002053783454207047,
      "grad_norm": 1.5443031787872314,
      "learning_rate": 9.990365154573717e-05,
      "loss": 5.0846,
      "step": 3
    },
    {
      "epoch": 0.0027383779389427293,
      "grad_norm": 1.4513391256332397,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.9153,
      "step": 4
    },
    {
      "epoch": 0.0034229724236784116,
      "grad_norm": 1.2515331506729126,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.8242,
      "step": 5
    },
    {
      "epoch": 0.004107566908414094,
      "grad_norm": 1.1466741561889648,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.8635,
      "step": 6
    },
    {
      "epoch": 0.004792161393149776,
      "grad_norm": 0.7819433808326721,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.9013,
      "step": 7
    },
    {
      "epoch": 0.005476755877885459,
      "grad_norm": 0.577840268611908,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.8079,
      "step": 8
    },
    {
      "epoch": 0.006161350362621141,
      "grad_norm": 0.8350602984428406,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.8048,
      "step": 9
    },
    {
      "epoch": 0.006845944847356823,
      "grad_norm": 0.8675013184547424,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.8008,
      "step": 10
    },
    {
      "epoch": 0.0075305393320925056,
      "grad_norm": 1.118022084236145,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.8584,
      "step": 11
    },
    {
      "epoch": 0.008215133816828188,
      "grad_norm": 0.6637853384017944,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.8433,
      "step": 12
    },
    {
      "epoch": 0.00889972830156387,
      "grad_norm": 1.2030086517333984,
      "learning_rate": 8.883279133655399e-05,
      "loss": 5.0964,
      "step": 13
    },
    {
      "epoch": 0.009584322786299553,
      "grad_norm": 0.891997218132019,
      "learning_rate": 8.681980515339464e-05,
      "loss": 5.0018,
      "step": 14
    },
    {
      "epoch": 0.010268917271035235,
      "grad_norm": 0.9329969882965088,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.7486,
      "step": 15
    },
    {
      "epoch": 0.010953511755770917,
      "grad_norm": 0.5448434948921204,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.6841,
      "step": 16
    },
    {
      "epoch": 0.0116381062405066,
      "grad_norm": 1.6073203086853027,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.5953,
      "step": 17
    },
    {
      "epoch": 0.012322700725242282,
      "grad_norm": 2.014742374420166,
      "learning_rate": 7.75e-05,
      "loss": 4.6134,
      "step": 18
    },
    {
      "epoch": 0.013007295209977964,
      "grad_norm": 2.2186100482940674,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.6135,
      "step": 19
    },
    {
      "epoch": 0.013691889694713646,
      "grad_norm": 1.8117921352386475,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.6247,
      "step": 20
    },
    {
      "epoch": 0.014376484179449329,
      "grad_norm": 0.8588649034500122,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.615,
      "step": 21
    },
    {
      "epoch": 0.015061078664185011,
      "grad_norm": 0.5354763865470886,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.609,
      "step": 22
    },
    {
      "epoch": 0.015745673148920693,
      "grad_norm": 0.7342782020568848,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.5877,
      "step": 23
    },
    {
      "epoch": 0.016430267633656376,
      "grad_norm": 0.5643114447593689,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.6211,
      "step": 24
    },
    {
      "epoch": 0.017114862118392058,
      "grad_norm": 0.4805735647678375,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.6834,
      "step": 25
    },
    {
      "epoch": 0.017114862118392058,
      "eval_loss": 4.552499294281006,
      "eval_runtime": 0.7173,
      "eval_samples_per_second": 69.705,
      "eval_steps_per_second": 18.123,
      "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": 5978313860317184.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}