{
  "best_metric": 0.235469788312912,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01297016861219196,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005188067444876783,
      "grad_norm": 7.257709980010986,
      "learning_rate": 5e-05,
      "loss": 0.8421,
      "step": 1
    },
    {
      "epoch": 0.0005188067444876783,
      "eval_loss": 0.9019366502761841,
      "eval_runtime": 437.3032,
      "eval_samples_per_second": 29.693,
      "eval_steps_per_second": 3.714,
      "step": 1
    },
    {
      "epoch": 0.0010376134889753567,
      "grad_norm": 9.514312744140625,
      "learning_rate": 0.0001,
      "loss": 0.7793,
      "step": 2
    },
    {
      "epoch": 0.0015564202334630351,
      "grad_norm": 13.657303810119629,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.8538,
      "step": 3
    },
    {
      "epoch": 0.0020752269779507134,
      "grad_norm": 13.498005867004395,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7789,
      "step": 4
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 15.755859375,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.6017,
      "step": 5
    },
    {
      "epoch": 0.0031128404669260703,
      "grad_norm": 13.434879302978516,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4315,
      "step": 6
    },
    {
      "epoch": 0.0036316472114137485,
      "grad_norm": 8.647991180419922,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.2934,
      "step": 7
    },
    {
      "epoch": 0.004150453955901427,
      "grad_norm": 5.960851192474365,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2742,
      "step": 8
    },
    {
      "epoch": 0.004669260700389105,
      "grad_norm": 5.692524433135986,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.254,
      "step": 9
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 6.573745250701904,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.266,
      "step": 10
    },
    {
      "epoch": 0.005706874189364461,
      "grad_norm": 7.913269996643066,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2703,
      "step": 11
    },
    {
      "epoch": 0.0062256809338521405,
      "grad_norm": 7.290318489074707,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.202,
      "step": 12
    },
    {
      "epoch": 0.006744487678339819,
      "grad_norm": 10.77153491973877,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.5624,
      "step": 13
    },
    {
      "epoch": 0.007263294422827497,
      "grad_norm": 13.511357307434082,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5687,
      "step": 14
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 9.808670043945312,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4122,
      "step": 15
    },
    {
      "epoch": 0.008300907911802853,
      "grad_norm": 7.290343761444092,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2995,
      "step": 16
    },
    {
      "epoch": 0.008819714656290532,
      "grad_norm": 8.092347145080566,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.3212,
      "step": 17
    },
    {
      "epoch": 0.00933852140077821,
      "grad_norm": 9.879920959472656,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2751,
      "step": 18
    },
    {
      "epoch": 0.009857328145265888,
      "grad_norm": 7.612329483032227,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.2201,
      "step": 19
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 5.5150322914123535,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1909,
      "step": 20
    },
    {
      "epoch": 0.010894941634241245,
      "grad_norm": 3.7366225719451904,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1765,
      "step": 21
    },
    {
      "epoch": 0.011413748378728923,
      "grad_norm": 4.036696434020996,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1671,
      "step": 22
    },
    {
      "epoch": 0.011932555123216601,
      "grad_norm": 5.270599365234375,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1808,
      "step": 23
    },
    {
      "epoch": 0.012451361867704281,
      "grad_norm": 8.023921012878418,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.2025,
      "step": 24
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 8.021526336669922,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.2274,
      "step": 25
    },
    {
      "epoch": 0.01297016861219196,
      "eval_loss": 0.235469788312912,
      "eval_runtime": 437.5793,
      "eval_samples_per_second": 29.675,
      "eval_steps_per_second": 3.711,
      "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": 1.4854232815855206e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}