{
  "best_metric": 0.23500166833400726,
  "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": 7.081730842590332,
      "learning_rate": 5e-05,
      "loss": 0.8421,
      "step": 1
    },
    {
      "epoch": 0.0005188067444876783,
      "eval_loss": 0.9019366502761841,
      "eval_runtime": 437.5703,
      "eval_samples_per_second": 29.675,
      "eval_steps_per_second": 3.711,
      "step": 1
    },
    {
      "epoch": 0.0010376134889753567,
      "grad_norm": 9.299199104309082,
      "learning_rate": 0.0001,
      "loss": 0.7793,
      "step": 2
    },
    {
      "epoch": 0.0015564202334630351,
      "grad_norm": 13.41754150390625,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.8543,
      "step": 3
    },
    {
      "epoch": 0.0020752269779507134,
      "grad_norm": 13.402043342590332,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7777,
      "step": 4
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 15.691983222961426,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5967,
      "step": 5
    },
    {
      "epoch": 0.0031128404669260703,
      "grad_norm": 13.358585357666016,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4273,
      "step": 6
    },
    {
      "epoch": 0.0036316472114137485,
      "grad_norm": 8.41795825958252,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.2902,
      "step": 7
    },
    {
      "epoch": 0.004150453955901427,
      "grad_norm": 5.917006492614746,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2733,
      "step": 8
    },
    {
      "epoch": 0.004669260700389105,
      "grad_norm": 5.552993297576904,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2524,
      "step": 9
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 6.439959526062012,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2657,
      "step": 10
    },
    {
      "epoch": 0.005706874189364461,
      "grad_norm": 7.775099277496338,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2694,
      "step": 11
    },
    {
      "epoch": 0.0062256809338521405,
      "grad_norm": 7.171384334564209,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.2017,
      "step": 12
    },
    {
      "epoch": 0.006744487678339819,
      "grad_norm": 10.638527870178223,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.5616,
      "step": 13
    },
    {
      "epoch": 0.007263294422827497,
      "grad_norm": 13.433341979980469,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5669,
      "step": 14
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 9.67660140991211,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4109,
      "step": 15
    },
    {
      "epoch": 0.008300907911802853,
      "grad_norm": 7.229345321655273,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2981,
      "step": 16
    },
    {
      "epoch": 0.008819714656290532,
      "grad_norm": 8.081628799438477,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.3206,
      "step": 17
    },
    {
      "epoch": 0.00933852140077821,
      "grad_norm": 9.81690502166748,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2764,
      "step": 18
    },
    {
      "epoch": 0.009857328145265888,
      "grad_norm": 7.637274265289307,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.221,
      "step": 19
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 5.528214931488037,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1908,
      "step": 20
    },
    {
      "epoch": 0.010894941634241245,
      "grad_norm": 3.7318928241729736,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1766,
      "step": 21
    },
    {
      "epoch": 0.011413748378728923,
      "grad_norm": 3.994821548461914,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1656,
      "step": 22
    },
    {
      "epoch": 0.011932555123216601,
      "grad_norm": 5.203790664672852,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1798,
      "step": 23
    },
    {
      "epoch": 0.012451361867704281,
      "grad_norm": 7.873574733734131,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.2008,
      "step": 24
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 7.9323577880859375,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.2257,
      "step": 25
    },
    {
      "epoch": 0.01297016861219196,
      "eval_loss": 0.23500166833400726,
      "eval_runtime": 437.1248,
      "eval_samples_per_second": 29.705,
      "eval_steps_per_second": 3.715,
      "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
}