{
  "best_metric": 0.447214812040329,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.1111111111111112,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 16.34016227722168,
      "learning_rate": 5e-05,
      "loss": 9.8289,
      "step": 1
    },
    {
      "epoch": 0.044444444444444446,
      "eval_loss": 13.514202117919922,
      "eval_runtime": 8.5195,
      "eval_samples_per_second": 5.869,
      "eval_steps_per_second": 1.526,
      "step": 1
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 21.221113204956055,
      "learning_rate": 0.0001,
      "loss": 12.676,
      "step": 2
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 27.357635498046875,
      "learning_rate": 9.990365154573717e-05,
      "loss": 14.1544,
      "step": 3
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 37.322933197021484,
      "learning_rate": 9.961501876182148e-05,
      "loss": 12.4999,
      "step": 4
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 17.118999481201172,
      "learning_rate": 9.913533761814537e-05,
      "loss": 7.8101,
      "step": 5
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 52.966583251953125,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.7518,
      "step": 6
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 71.5065689086914,
      "learning_rate": 9.761185582727977e-05,
      "loss": 7.0985,
      "step": 7
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 45.55967712402344,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.9202,
      "step": 8
    },
    {
      "epoch": 0.4,
      "grad_norm": 83.13799285888672,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.9406,
      "step": 9
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 59.92570495605469,
      "learning_rate": 9.397114317029975e-05,
      "loss": 5.2075,
      "step": 10
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 24.67129898071289,
      "learning_rate": 9.241613255361455e-05,
      "loss": 3.131,
      "step": 11
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 39.77735900878906,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.1664,
      "step": 12
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 18.40007972717285,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.6304,
      "step": 13
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 16.40590476989746,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.3554,
      "step": 14
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 18.445859909057617,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.8851,
      "step": 15
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 11.208172798156738,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.0625,
      "step": 16
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 11.166001319885254,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.6406,
      "step": 17
    },
    {
      "epoch": 0.8,
      "grad_norm": 11.158333778381348,
      "learning_rate": 7.75e-05,
      "loss": 1.561,
      "step": 18
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 9.224180221557617,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.1925,
      "step": 19
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 23.98605728149414,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.8318,
      "step": 20
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 11.465433120727539,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.3753,
      "step": 21
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 4.563766002655029,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.4548,
      "step": 22
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 13.37357234954834,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.986,
      "step": 23
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 5.592074871063232,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.3582,
      "step": 24
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 4.71364164352417,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.3453,
      "step": 25
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 0.447214812040329,
      "eval_runtime": 8.5804,
      "eval_samples_per_second": 5.827,
      "eval_steps_per_second": 1.515,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.74998392174805e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}