{
  "best_metric": 0.22793392837047577,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.18709073900841908,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007483629560336763,
      "grad_norm": 2668.53466796875,
      "learning_rate": 5e-05,
      "loss": 4.3827,
      "step": 1
    },
    {
      "epoch": 0.007483629560336763,
      "eval_loss": 4.760346412658691,
      "eval_runtime": 26.3843,
      "eval_samples_per_second": 34.149,
      "eval_steps_per_second": 4.283,
      "step": 1
    },
    {
      "epoch": 0.014967259120673527,
      "grad_norm": 2783.445068359375,
      "learning_rate": 0.0001,
      "loss": 4.4899,
      "step": 2
    },
    {
      "epoch": 0.02245088868101029,
      "grad_norm": 394.49444580078125,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.1667,
      "step": 3
    },
    {
      "epoch": 0.029934518241347054,
      "grad_norm": 595.1309814453125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.8192,
      "step": 4
    },
    {
      "epoch": 0.037418147801683815,
      "grad_norm": 505.4878845214844,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5339,
      "step": 5
    },
    {
      "epoch": 0.04490177736202058,
      "grad_norm": 969.9791259765625,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5082,
      "step": 6
    },
    {
      "epoch": 0.052385406922357346,
      "grad_norm": 246.9044189453125,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.1231,
      "step": 7
    },
    {
      "epoch": 0.05986903648269411,
      "grad_norm": 28.268033981323242,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0382,
      "step": 8
    },
    {
      "epoch": 0.06735266604303088,
      "grad_norm": 28.354206085205078,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0281,
      "step": 9
    },
    {
      "epoch": 0.07483629560336763,
      "grad_norm": 20.920122146606445,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0122,
      "step": 10
    },
    {
      "epoch": 0.0823199251637044,
      "grad_norm": 16.22517204284668,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0104,
      "step": 11
    },
    {
      "epoch": 0.08980355472404115,
      "grad_norm": 20.09650421142578,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0057,
      "step": 12
    },
    {
      "epoch": 0.09728718428437792,
      "grad_norm": 1341.5556640625,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.342,
      "step": 13
    },
    {
      "epoch": 0.10477081384471469,
      "grad_norm": 277.5860900878906,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7457,
      "step": 14
    },
    {
      "epoch": 0.11225444340505145,
      "grad_norm": 130.9478302001953,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4444,
      "step": 15
    },
    {
      "epoch": 0.11973807296538821,
      "grad_norm": 233.44265747070312,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.398,
      "step": 16
    },
    {
      "epoch": 0.12722170252572498,
      "grad_norm": 54.11774444580078,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2516,
      "step": 17
    },
    {
      "epoch": 0.13470533208606175,
      "grad_norm": 24.96857452392578,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0276,
      "step": 18
    },
    {
      "epoch": 0.1421889616463985,
      "grad_norm": 26.93854522705078,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0369,
      "step": 19
    },
    {
      "epoch": 0.14967259120673526,
      "grad_norm": 16.38790512084961,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0276,
      "step": 20
    },
    {
      "epoch": 0.15715622076707203,
      "grad_norm": 23.881519317626953,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0387,
      "step": 21
    },
    {
      "epoch": 0.1646398503274088,
      "grad_norm": 30.489585876464844,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.069,
      "step": 22
    },
    {
      "epoch": 0.17212347988774557,
      "grad_norm": 15.927953720092773,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0301,
      "step": 23
    },
    {
      "epoch": 0.1796071094480823,
      "grad_norm": 553.0681762695312,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1495,
      "step": 24
    },
    {
      "epoch": 0.18709073900841908,
      "grad_norm": 40.822509765625,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0246,
      "step": 25
    },
    {
      "epoch": 0.18709073900841908,
      "eval_loss": 0.22793392837047577,
      "eval_runtime": 26.3513,
      "eval_samples_per_second": 34.192,
      "eval_steps_per_second": 4.288,
      "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": 2.829013890367488e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}