{
  "best_metric": 0.7922729849815369,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3147128245476003,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012588512981904013,
      "grad_norm": 0.9374328851699829,
      "learning_rate": 5e-05,
      "loss": 2.2967,
      "step": 1
    },
    {
      "epoch": 0.012588512981904013,
      "eval_loss": 3.410280227661133,
      "eval_runtime": 28.691,
      "eval_samples_per_second": 18.682,
      "eval_steps_per_second": 2.335,
      "step": 1
    },
    {
      "epoch": 0.025177025963808025,
      "grad_norm": 1.306756854057312,
      "learning_rate": 0.0001,
      "loss": 2.7038,
      "step": 2
    },
    {
      "epoch": 0.03776553894571204,
      "grad_norm": 1.3629939556121826,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.5091,
      "step": 3
    },
    {
      "epoch": 0.05035405192761605,
      "grad_norm": 1.4472253322601318,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.5138,
      "step": 4
    },
    {
      "epoch": 0.06294256490952006,
      "grad_norm": 2.081310749053955,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.539,
      "step": 5
    },
    {
      "epoch": 0.07553107789142408,
      "grad_norm": 1.6973925828933716,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.0807,
      "step": 6
    },
    {
      "epoch": 0.08811959087332809,
      "grad_norm": 1.6589587926864624,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0102,
      "step": 7
    },
    {
      "epoch": 0.1007081038552321,
      "grad_norm": 2.2432773113250732,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0128,
      "step": 8
    },
    {
      "epoch": 0.11329661683713611,
      "grad_norm": 3.0825912952423096,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.8282,
      "step": 9
    },
    {
      "epoch": 0.12588512981904013,
      "grad_norm": 2.0198371410369873,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5822,
      "step": 10
    },
    {
      "epoch": 0.13847364280094415,
      "grad_norm": 1.7006489038467407,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.4039,
      "step": 11
    },
    {
      "epoch": 0.15106215578284815,
      "grad_norm": 1.9521818161010742,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.4428,
      "step": 12
    },
    {
      "epoch": 0.16365066876475218,
      "grad_norm": 1.730639100074768,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1403,
      "step": 13
    },
    {
      "epoch": 0.17623918174665618,
      "grad_norm": 1.5531525611877441,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3026,
      "step": 14
    },
    {
      "epoch": 0.1888276947285602,
      "grad_norm": 1.7489203214645386,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.087,
      "step": 15
    },
    {
      "epoch": 0.2014162077104642,
      "grad_norm": 1.7740451097488403,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.2439,
      "step": 16
    },
    {
      "epoch": 0.21400472069236823,
      "grad_norm": 1.3824913501739502,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1082,
      "step": 17
    },
    {
      "epoch": 0.22659323367427223,
      "grad_norm": 0.8740619421005249,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0499,
      "step": 18
    },
    {
      "epoch": 0.23918174665617625,
      "grad_norm": 0.7334346175193787,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.9394,
      "step": 19
    },
    {
      "epoch": 0.25177025963808025,
      "grad_norm": 1.1040862798690796,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0259,
      "step": 20
    },
    {
      "epoch": 0.26435877261998425,
      "grad_norm": 1.1865637302398682,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9681,
      "step": 21
    },
    {
      "epoch": 0.2769472856018883,
      "grad_norm": 0.9018222093582153,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.979,
      "step": 22
    },
    {
      "epoch": 0.2895357985837923,
      "grad_norm": 1.158233642578125,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8494,
      "step": 23
    },
    {
      "epoch": 0.3021243115656963,
      "grad_norm": 1.046151876449585,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.851,
      "step": 24
    },
    {
      "epoch": 0.3147128245476003,
      "grad_norm": 1.4118893146514893,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.808,
      "step": 25
    },
    {
      "epoch": 0.3147128245476003,
      "eval_loss": 0.7922729849815369,
      "eval_runtime": 28.7104,
      "eval_samples_per_second": 18.669,
      "eval_steps_per_second": 2.334,
      "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": 5.555785010511872e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}