{
  "best_metric": 10.3701753616333,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.645682001614205,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0258272800645682,
      "grad_norm": 0.14458106458187103,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3967,
      "step": 1
    },
    {
      "epoch": 0.0258272800645682,
      "eval_loss": 10.38502311706543,
      "eval_runtime": 0.1482,
      "eval_samples_per_second": 337.285,
      "eval_steps_per_second": 87.694,
      "step": 1
    },
    {
      "epoch": 0.0516545601291364,
      "grad_norm": 0.19388781487941742,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.4055,
      "step": 2
    },
    {
      "epoch": 0.0774818401937046,
      "grad_norm": 0.13940967619419098,
      "learning_rate": 0.0001,
      "loss": 10.3947,
      "step": 3
    },
    {
      "epoch": 0.1033091202582728,
      "grad_norm": 0.12940029799938202,
      "learning_rate": 9.997376600647783e-05,
      "loss": 10.39,
      "step": 4
    },
    {
      "epoch": 0.129136400322841,
      "grad_norm": 0.12409521639347076,
      "learning_rate": 9.989509461357426e-05,
      "loss": 10.383,
      "step": 5
    },
    {
      "epoch": 0.1549636803874092,
      "grad_norm": 0.11843808740377426,
      "learning_rate": 9.976407754861426e-05,
      "loss": 10.3812,
      "step": 6
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 0.11526809632778168,
      "learning_rate": 9.958086757163489e-05,
      "loss": 10.3722,
      "step": 7
    },
    {
      "epoch": 0.2066182405165456,
      "grad_norm": 0.11756883561611176,
      "learning_rate": 9.934567829727386e-05,
      "loss": 10.3561,
      "step": 8
    },
    {
      "epoch": 0.2324455205811138,
      "grad_norm": 0.14288835227489471,
      "learning_rate": 9.905878394570453e-05,
      "loss": 10.3812,
      "step": 9
    },
    {
      "epoch": 0.258272800645682,
      "grad_norm": 0.1054273471236229,
      "learning_rate": 9.872051902290737e-05,
      "loss": 10.3776,
      "step": 10
    },
    {
      "epoch": 0.2841000807102502,
      "grad_norm": 0.21361760795116425,
      "learning_rate": 9.833127793065098e-05,
      "loss": 10.4013,
      "step": 11
    },
    {
      "epoch": 0.3099273607748184,
      "grad_norm": 0.13051673769950867,
      "learning_rate": 9.789151450663723e-05,
      "loss": 10.3836,
      "step": 12
    },
    {
      "epoch": 0.3357546408393866,
      "grad_norm": 0.13624922931194305,
      "learning_rate": 9.740174149534693e-05,
      "loss": 10.3847,
      "step": 13
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 0.13448677957057953,
      "learning_rate": 9.686252995020249e-05,
      "loss": 10.3821,
      "step": 14
    },
    {
      "epoch": 0.387409200968523,
      "grad_norm": 0.13489721715450287,
      "learning_rate": 9.627450856774539e-05,
      "loss": 10.3781,
      "step": 15
    },
    {
      "epoch": 0.4132364810330912,
      "grad_norm": 0.11860419064760208,
      "learning_rate": 9.563836295460398e-05,
      "loss": 10.3716,
      "step": 16
    },
    {
      "epoch": 0.4390637610976594,
      "grad_norm": 0.12369117885828018,
      "learning_rate": 9.495483482810688e-05,
      "loss": 10.357,
      "step": 17
    },
    {
      "epoch": 0.4648910411622276,
      "grad_norm": 0.12533077597618103,
      "learning_rate": 9.422472115147382e-05,
      "loss": 10.3728,
      "step": 18
    },
    {
      "epoch": 0.4907183212267958,
      "grad_norm": 0.1503569632768631,
      "learning_rate": 9.3448873204592e-05,
      "loss": 10.3781,
      "step": 19
    },
    {
      "epoch": 0.516545601291364,
      "grad_norm": 0.1492878496646881,
      "learning_rate": 9.2628195591462e-05,
      "loss": 10.3794,
      "step": 20
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.2185596376657486,
      "learning_rate": 9.176364518546989e-05,
      "loss": 10.3976,
      "step": 21
    },
    {
      "epoch": 0.5682001614205004,
      "grad_norm": 0.14859223365783691,
      "learning_rate": 9.08562300137157e-05,
      "loss": 10.3817,
      "step": 22
    },
    {
      "epoch": 0.5940274414850686,
      "grad_norm": 0.14766570925712585,
      "learning_rate": 8.990700808169889e-05,
      "loss": 10.376,
      "step": 23
    },
    {
      "epoch": 0.6198547215496368,
      "grad_norm": 0.14743873476982117,
      "learning_rate": 8.891708613973126e-05,
      "loss": 10.3707,
      "step": 24
    },
    {
      "epoch": 0.645682001614205,
      "grad_norm": 0.14462894201278687,
      "learning_rate": 8.788761839251559e-05,
      "loss": 10.3691,
      "step": 25
    },
    {
      "epoch": 0.645682001614205,
      "eval_loss": 10.3701753616333,
      "eval_runtime": 0.141,
      "eval_samples_per_second": 354.551,
      "eval_steps_per_second": 92.183,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 25326710423552.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}