{
  "best_metric": 11.936851501464844,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.22727272727272727,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 0.014407745562493801,
      "learning_rate": 5e-05,
      "loss": 11.9324,
      "step": 1
    },
    {
      "epoch": 0.00909090909090909,
      "eval_loss": 11.940053939819336,
      "eval_runtime": 1.5718,
      "eval_samples_per_second": 471.441,
      "eval_steps_per_second": 59.169,
      "step": 1
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.020456792786717415,
      "learning_rate": 0.0001,
      "loss": 11.9359,
      "step": 2
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 0.02752542309463024,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9359,
      "step": 3
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.030046707019209862,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9355,
      "step": 4
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.03253328800201416,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9362,
      "step": 5
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.03853551298379898,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.9368,
      "step": 6
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 0.047178175300359726,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9367,
      "step": 7
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.05311514064669609,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9372,
      "step": 8
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 0.05621656775474548,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9387,
      "step": 9
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.08180534094572067,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9402,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.10444722324609756,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.9424,
      "step": 11
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.1504172831773758,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9463,
      "step": 12
    },
    {
      "epoch": 0.11818181818181818,
      "grad_norm": 0.027267219498753548,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9336,
      "step": 13
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 0.021916711702942848,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9336,
      "step": 14
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.025460882112383842,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9342,
      "step": 15
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.03715614974498749,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9351,
      "step": 16
    },
    {
      "epoch": 0.15454545454545454,
      "grad_norm": 0.04742095246911049,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9355,
      "step": 17
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.04686274006962776,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9349,
      "step": 18
    },
    {
      "epoch": 0.17272727272727273,
      "grad_norm": 0.05396494269371033,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.936,
      "step": 19
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.06768876314163208,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9369,
      "step": 20
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 0.07629425823688507,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9363,
      "step": 21
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.09198444336652756,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9379,
      "step": 22
    },
    {
      "epoch": 0.20909090909090908,
      "grad_norm": 0.12001596391201019,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9388,
      "step": 23
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.16391249001026154,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9413,
      "step": 24
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.23358383774757385,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9449,
      "step": 25
    },
    {
      "epoch": 0.22727272727272727,
      "eval_loss": 11.936851501464844,
      "eval_runtime": 1.576,
      "eval_samples_per_second": 470.181,
      "eval_steps_per_second": 59.011,
      "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": 523201806336.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}