{
  "best_metric": 0.4452657997608185,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2097535395909806,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008390141583639224,
      "grad_norm": 176.95970153808594,
      "learning_rate": 5e-05,
      "loss": 83.8291,
      "step": 1
    },
    {
      "epoch": 0.008390141583639224,
      "eval_loss": 6.332316875457764,
      "eval_runtime": 20.7652,
      "eval_samples_per_second": 38.67,
      "eval_steps_per_second": 4.864,
      "step": 1
    },
    {
      "epoch": 0.016780283167278448,
      "grad_norm": 169.97886657714844,
      "learning_rate": 0.0001,
      "loss": 88.4324,
      "step": 2
    },
    {
      "epoch": 0.025170424750917672,
      "grad_norm": 191.46353149414062,
      "learning_rate": 9.989294616193017e-05,
      "loss": 81.68,
      "step": 3
    },
    {
      "epoch": 0.033560566334556896,
      "grad_norm": 114.6288833618164,
      "learning_rate": 9.957224306869053e-05,
      "loss": 56.2902,
      "step": 4
    },
    {
      "epoch": 0.04195070791819612,
      "grad_norm": 83.60888671875,
      "learning_rate": 9.903926402016153e-05,
      "loss": 45.9769,
      "step": 5
    },
    {
      "epoch": 0.050340849501835344,
      "grad_norm": 144.06565856933594,
      "learning_rate": 9.829629131445342e-05,
      "loss": 43.8172,
      "step": 6
    },
    {
      "epoch": 0.05873099108547457,
      "grad_norm": 93.93113708496094,
      "learning_rate": 9.73465064747553e-05,
      "loss": 35.7606,
      "step": 7
    },
    {
      "epoch": 0.06712113266911379,
      "grad_norm": 82.48625183105469,
      "learning_rate": 9.619397662556435e-05,
      "loss": 31.5253,
      "step": 8
    },
    {
      "epoch": 0.07551127425275302,
      "grad_norm": 87.17147064208984,
      "learning_rate": 9.484363707663442e-05,
      "loss": 27.6899,
      "step": 9
    },
    {
      "epoch": 0.08390141583639224,
      "grad_norm": 68.36941528320312,
      "learning_rate": 9.330127018922194e-05,
      "loss": 24.6904,
      "step": 10
    },
    {
      "epoch": 0.09229155742003146,
      "grad_norm": 65.01605987548828,
      "learning_rate": 9.157348061512727e-05,
      "loss": 20.0167,
      "step": 11
    },
    {
      "epoch": 0.10068169900367069,
      "grad_norm": 63.118526458740234,
      "learning_rate": 8.966766701456177e-05,
      "loss": 16.3101,
      "step": 12
    },
    {
      "epoch": 0.10907184058730991,
      "grad_norm": 73.39042663574219,
      "learning_rate": 8.759199037394887e-05,
      "loss": 17.0812,
      "step": 13
    },
    {
      "epoch": 0.11746198217094914,
      "grad_norm": 82.60930633544922,
      "learning_rate": 8.535533905932738e-05,
      "loss": 22.1918,
      "step": 14
    },
    {
      "epoch": 0.12585212375458835,
      "grad_norm": 69.67918395996094,
      "learning_rate": 8.296729075500344e-05,
      "loss": 17.4309,
      "step": 15
    },
    {
      "epoch": 0.13424226533822758,
      "grad_norm": 55.29849624633789,
      "learning_rate": 8.043807145043604e-05,
      "loss": 15.0294,
      "step": 16
    },
    {
      "epoch": 0.1426324069218668,
      "grad_norm": 45.169612884521484,
      "learning_rate": 7.777851165098012e-05,
      "loss": 12.1589,
      "step": 17
    },
    {
      "epoch": 0.15102254850550603,
      "grad_norm": 49.79930877685547,
      "learning_rate": 7.500000000000001e-05,
      "loss": 12.7402,
      "step": 18
    },
    {
      "epoch": 0.15941269008914524,
      "grad_norm": 50.261138916015625,
      "learning_rate": 7.211443451095007e-05,
      "loss": 13.9272,
      "step": 19
    },
    {
      "epoch": 0.16780283167278448,
      "grad_norm": 52.632110595703125,
      "learning_rate": 6.91341716182545e-05,
      "loss": 14.9553,
      "step": 20
    },
    {
      "epoch": 0.1761929732564237,
      "grad_norm": 39.690181732177734,
      "learning_rate": 6.607197326515808e-05,
      "loss": 9.3049,
      "step": 21
    },
    {
      "epoch": 0.18458311484006293,
      "grad_norm": 53.46142578125,
      "learning_rate": 6.294095225512603e-05,
      "loss": 9.9428,
      "step": 22
    },
    {
      "epoch": 0.19297325642370214,
      "grad_norm": 44.59263610839844,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 7.0882,
      "step": 23
    },
    {
      "epoch": 0.20136339800734138,
      "grad_norm": 51.48603439331055,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 7.3851,
      "step": 24
    },
    {
      "epoch": 0.2097535395909806,
      "grad_norm": 60.213985443115234,
      "learning_rate": 5.327015646150716e-05,
      "loss": 6.1465,
      "step": 25
    },
    {
      "epoch": 0.2097535395909806,
      "eval_loss": 0.4452657997608185,
      "eval_runtime": 20.7198,
      "eval_samples_per_second": 38.755,
      "eval_steps_per_second": 4.875,
      "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": 2.8307787998035968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}