{
  "best_metric": 3.688027858734131,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0035167153878277687,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014066861551311076,
      "grad_norm": 0.9427841305732727,
      "learning_rate": 5e-05,
      "loss": 2.2525,
      "step": 1
    },
    {
      "epoch": 0.00014066861551311076,
      "eval_loss": 5.381374359130859,
      "eval_runtime": 4.305,
      "eval_samples_per_second": 11.614,
      "eval_steps_per_second": 3.02,
      "step": 1
    },
    {
      "epoch": 0.00028133723102622153,
      "grad_norm": 1.4493043422698975,
      "learning_rate": 0.0001,
      "loss": 3.0518,
      "step": 2
    },
    {
      "epoch": 0.00042200584653933227,
      "grad_norm": 1.8600473403930664,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.6448,
      "step": 3
    },
    {
      "epoch": 0.0005626744620524431,
      "grad_norm": 2.302962303161621,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.4023,
      "step": 4
    },
    {
      "epoch": 0.0007033430775655537,
      "grad_norm": 3.376417875289917,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.6614,
      "step": 5
    },
    {
      "epoch": 0.0008440116930786645,
      "grad_norm": 3.2473976612091064,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.4394,
      "step": 6
    },
    {
      "epoch": 0.0009846803085917753,
      "grad_norm": 2.340790033340454,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.2634,
      "step": 7
    },
    {
      "epoch": 0.0011253489241048861,
      "grad_norm": 2.2660000324249268,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.3473,
      "step": 8
    },
    {
      "epoch": 0.0012660175396179967,
      "grad_norm": 2.196218729019165,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.26,
      "step": 9
    },
    {
      "epoch": 0.0014066861551311075,
      "grad_norm": 2.6228277683258057,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.171,
      "step": 10
    },
    {
      "epoch": 0.0015473547706442183,
      "grad_norm": 3.1706738471984863,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.4074,
      "step": 11
    },
    {
      "epoch": 0.001688023386157329,
      "grad_norm": 4.587759494781494,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.6637,
      "step": 12
    },
    {
      "epoch": 0.0018286920016704399,
      "grad_norm": 2.9576611518859863,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.4479,
      "step": 13
    },
    {
      "epoch": 0.0019693606171835507,
      "grad_norm": 3.024545907974243,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.8594,
      "step": 14
    },
    {
      "epoch": 0.0021100292326966612,
      "grad_norm": 2.2302956581115723,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.9605,
      "step": 15
    },
    {
      "epoch": 0.0022506978482097722,
      "grad_norm": 1.8585838079452515,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.3364,
      "step": 16
    },
    {
      "epoch": 0.002391366463722883,
      "grad_norm": 2.91164493560791,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.79,
      "step": 17
    },
    {
      "epoch": 0.0025320350792359934,
      "grad_norm": 2.227503538131714,
      "learning_rate": 7.75e-05,
      "loss": 3.743,
      "step": 18
    },
    {
      "epoch": 0.0026727036947491044,
      "grad_norm": 1.9422775506973267,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.9933,
      "step": 19
    },
    {
      "epoch": 0.002813372310262215,
      "grad_norm": 1.9657392501831055,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.963,
      "step": 20
    },
    {
      "epoch": 0.002954040925775326,
      "grad_norm": 2.104684591293335,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.8063,
      "step": 21
    },
    {
      "epoch": 0.0030947095412884366,
      "grad_norm": 2.2109615802764893,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.0589,
      "step": 22
    },
    {
      "epoch": 0.0032353781568015476,
      "grad_norm": 2.330768585205078,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.9557,
      "step": 23
    },
    {
      "epoch": 0.003376046772314658,
      "grad_norm": 2.38495135307312,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.3077,
      "step": 24
    },
    {
      "epoch": 0.0035167153878277687,
      "grad_norm": 3.6864495277404785,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.858,
      "step": 25
    },
    {
      "epoch": 0.0035167153878277687,
      "eval_loss": 3.688027858734131,
      "eval_runtime": 4.3449,
      "eval_samples_per_second": 11.508,
      "eval_steps_per_second": 2.992,
      "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
}