{
  "best_metric": 0.8075627684593201,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.02629935237844768,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010519740951379073,
      "grad_norm": 37.66078567504883,
      "learning_rate": 5e-05,
      "loss": 14.8109,
      "step": 1
    },
    {
      "epoch": 0.0010519740951379073,
      "eval_loss": 13.268001556396484,
      "eval_runtime": 2.0272,
      "eval_samples_per_second": 24.664,
      "eval_steps_per_second": 6.413,
      "step": 1
    },
    {
      "epoch": 0.0021039481902758147,
      "grad_norm": 48.14912033081055,
      "learning_rate": 0.0001,
      "loss": 14.1398,
      "step": 2
    },
    {
      "epoch": 0.0031559222854137215,
      "grad_norm": 41.73773956298828,
      "learning_rate": 9.990365154573717e-05,
      "loss": 12.5357,
      "step": 3
    },
    {
      "epoch": 0.004207896380551629,
      "grad_norm": 39.7030029296875,
      "learning_rate": 9.961501876182148e-05,
      "loss": 7.3614,
      "step": 4
    },
    {
      "epoch": 0.005259870475689536,
      "grad_norm": 23.408571243286133,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.6285,
      "step": 5
    },
    {
      "epoch": 0.006311844570827443,
      "grad_norm": 23.954805374145508,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.3564,
      "step": 6
    },
    {
      "epoch": 0.007363818665965351,
      "grad_norm": 12.64648723602295,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.4816,
      "step": 7
    },
    {
      "epoch": 0.008415792761103259,
      "grad_norm": 7.248321533203125,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.0535,
      "step": 8
    },
    {
      "epoch": 0.009467766856241165,
      "grad_norm": 4.235668659210205,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.8985,
      "step": 9
    },
    {
      "epoch": 0.010519740951379072,
      "grad_norm": 3.8979365825653076,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.8346,
      "step": 10
    },
    {
      "epoch": 0.01157171504651698,
      "grad_norm": 6.265169620513916,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.853,
      "step": 11
    },
    {
      "epoch": 0.012623689141654886,
      "grad_norm": 6.652163028717041,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.8676,
      "step": 12
    },
    {
      "epoch": 0.013675663236792795,
      "grad_norm": 12.269131660461426,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.1406,
      "step": 13
    },
    {
      "epoch": 0.014727637331930702,
      "grad_norm": 6.396784782409668,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.9183,
      "step": 14
    },
    {
      "epoch": 0.01577961142706861,
      "grad_norm": 3.7699356079101562,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.827,
      "step": 15
    },
    {
      "epoch": 0.016831585522206517,
      "grad_norm": 2.2097628116607666,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.8275,
      "step": 16
    },
    {
      "epoch": 0.017883559617344422,
      "grad_norm": 1.7083959579467773,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.8225,
      "step": 17
    },
    {
      "epoch": 0.01893553371248233,
      "grad_norm": 2.439757823944092,
      "learning_rate": 7.75e-05,
      "loss": 0.828,
      "step": 18
    },
    {
      "epoch": 0.019987507807620236,
      "grad_norm": 2.4405243396759033,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.812,
      "step": 19
    },
    {
      "epoch": 0.021039481902758145,
      "grad_norm": 2.1622493267059326,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.8154,
      "step": 20
    },
    {
      "epoch": 0.022091455997896053,
      "grad_norm": 2.0287113189697266,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.8343,
      "step": 21
    },
    {
      "epoch": 0.02314343009303396,
      "grad_norm": 2.6538174152374268,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.8351,
      "step": 22
    },
    {
      "epoch": 0.024195404188171867,
      "grad_norm": 2.780940294265747,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.8283,
      "step": 23
    },
    {
      "epoch": 0.025247378283309772,
      "grad_norm": 2.008140802383423,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.8269,
      "step": 24
    },
    {
      "epoch": 0.02629935237844768,
      "grad_norm": 1.1456310749053955,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.8082,
      "step": 25
    },
    {
      "epoch": 0.02629935237844768,
      "eval_loss": 0.8075627684593201,
      "eval_runtime": 2.0782,
      "eval_samples_per_second": 24.06,
      "eval_steps_per_second": 6.256,
      "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": 8.26272811885527e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}