{
  "best_metric": 1.315967321395874,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1736111111111111,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006944444444444444,
      "grad_norm": 3.476346254348755,
      "learning_rate": 5e-05,
      "loss": 5.4127,
      "step": 1
    },
    {
      "epoch": 0.006944444444444444,
      "eval_loss": 4.7398810386657715,
      "eval_runtime": 29.857,
      "eval_samples_per_second": 32.488,
      "eval_steps_per_second": 4.086,
      "step": 1
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 3.7576146125793457,
      "learning_rate": 0.0001,
      "loss": 4.5563,
      "step": 2
    },
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 3.2495226860046387,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.4202,
      "step": 3
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 2.8715317249298096,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.7515,
      "step": 4
    },
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 3.1827681064605713,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.1039,
      "step": 5
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 3.257744789123535,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.4059,
      "step": 6
    },
    {
      "epoch": 0.04861111111111111,
      "grad_norm": 3.1038901805877686,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.8887,
      "step": 7
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 3.184278726577759,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5376,
      "step": 8
    },
    {
      "epoch": 0.0625,
      "grad_norm": 2.082414150238037,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.3516,
      "step": 9
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 1.6695497035980225,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.3557,
      "step": 10
    },
    {
      "epoch": 0.0763888888888889,
      "grad_norm": 1.8141134977340698,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.4042,
      "step": 11
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.9131998419761658,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3845,
      "step": 12
    },
    {
      "epoch": 0.09027777777777778,
      "grad_norm": 8.301287651062012,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.0785,
      "step": 13
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 1.9383556842803955,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2627,
      "step": 14
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.2070971727371216,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2195,
      "step": 15
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.8308581709861755,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.1975,
      "step": 16
    },
    {
      "epoch": 0.11805555555555555,
      "grad_norm": 0.7211664319038391,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1921,
      "step": 17
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.5430946946144104,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2082,
      "step": 18
    },
    {
      "epoch": 0.13194444444444445,
      "grad_norm": 1.2237274646759033,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2241,
      "step": 19
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 0.4934002757072449,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2346,
      "step": 20
    },
    {
      "epoch": 0.14583333333333334,
      "grad_norm": 0.44239938259124756,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2009,
      "step": 21
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 0.3797169625759125,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.2146,
      "step": 22
    },
    {
      "epoch": 0.1597222222222222,
      "grad_norm": 0.38971444964408875,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.2059,
      "step": 23
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.097565770149231,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.26,
      "step": 24
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 0.7389172911643982,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.2768,
      "step": 25
    },
    {
      "epoch": 0.1736111111111111,
      "eval_loss": 1.315967321395874,
      "eval_runtime": 30.0845,
      "eval_samples_per_second": 32.243,
      "eval_steps_per_second": 4.055,
      "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": 2.89638977248428e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}