{
  "best_metric": 1.382283329963684,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.005629996622002027,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022519986488008108,
      "grad_norm": 2.1278951168060303,
      "learning_rate": 5e-05,
      "loss": 3.074,
      "step": 1
    },
    {
      "epoch": 0.00022519986488008108,
      "eval_loss": 4.716169834136963,
      "eval_runtime": 4.3621,
      "eval_samples_per_second": 11.462,
      "eval_steps_per_second": 2.98,
      "step": 1
    },
    {
      "epoch": 0.00045039972976016217,
      "grad_norm": 2.8499019145965576,
      "learning_rate": 0.0001,
      "loss": 3.7294,
      "step": 2
    },
    {
      "epoch": 0.0006755995946402432,
      "grad_norm": 3.092931032180786,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.7785,
      "step": 3
    },
    {
      "epoch": 0.0009007994595203243,
      "grad_norm": 3.2609915733337402,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.1929,
      "step": 4
    },
    {
      "epoch": 0.0011259993244004053,
      "grad_norm": 4.475097179412842,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.7112,
      "step": 5
    },
    {
      "epoch": 0.0013511991892804864,
      "grad_norm": 2.9876198768615723,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.2643,
      "step": 6
    },
    {
      "epoch": 0.0015763990541605676,
      "grad_norm": 2.384199380874634,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.0521,
      "step": 7
    },
    {
      "epoch": 0.0018015989190406487,
      "grad_norm": 3.000969648361206,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.8703,
      "step": 8
    },
    {
      "epoch": 0.0020267987839207298,
      "grad_norm": 2.2856993675231934,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.8155,
      "step": 9
    },
    {
      "epoch": 0.0022519986488008107,
      "grad_norm": 3.448403835296631,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.7403,
      "step": 10
    },
    {
      "epoch": 0.002477198513680892,
      "grad_norm": 2.4281277656555176,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.6285,
      "step": 11
    },
    {
      "epoch": 0.002702398378560973,
      "grad_norm": 1.6444188356399536,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.7825,
      "step": 12
    },
    {
      "epoch": 0.0029275982434410538,
      "grad_norm": 3.361898899078369,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.7924,
      "step": 13
    },
    {
      "epoch": 0.003152798108321135,
      "grad_norm": 2.4469213485717773,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.6112,
      "step": 14
    },
    {
      "epoch": 0.003377997973201216,
      "grad_norm": 1.2440874576568604,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.5038,
      "step": 15
    },
    {
      "epoch": 0.0036031978380812973,
      "grad_norm": 1.0188878774642944,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.422,
      "step": 16
    },
    {
      "epoch": 0.0038283977029613782,
      "grad_norm": 1.1848514080047607,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.4293,
      "step": 17
    },
    {
      "epoch": 0.0040535975678414595,
      "grad_norm": 1.1049160957336426,
      "learning_rate": 7.75e-05,
      "loss": 1.3361,
      "step": 18
    },
    {
      "epoch": 0.00427879743272154,
      "grad_norm": 1.1141437292099,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.5148,
      "step": 19
    },
    {
      "epoch": 0.004503997297601621,
      "grad_norm": 0.9767174124717712,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.455,
      "step": 20
    },
    {
      "epoch": 0.004729197162481703,
      "grad_norm": 1.102776288986206,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.4185,
      "step": 21
    },
    {
      "epoch": 0.004954397027361784,
      "grad_norm": 1.1417127847671509,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.4333,
      "step": 22
    },
    {
      "epoch": 0.0051795968922418644,
      "grad_norm": 1.070078730583191,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.4496,
      "step": 23
    },
    {
      "epoch": 0.005404796757121946,
      "grad_norm": 0.9801068305969238,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.4157,
      "step": 24
    },
    {
      "epoch": 0.005629996622002027,
      "grad_norm": 1.6465044021606445,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.6247,
      "step": 25
    },
    {
      "epoch": 0.005629996622002027,
      "eval_loss": 1.382283329963684,
      "eval_runtime": 4.3747,
      "eval_samples_per_second": 11.429,
      "eval_steps_per_second": 2.972,
      "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": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}