{
  "best_metric": 1.1425410509109497,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2336448598130841,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.3978344798088074,
      "learning_rate": 5e-05,
      "loss": 1.9398,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 1.7340189218521118,
      "eval_runtime": 8.5936,
      "eval_samples_per_second": 83.9,
      "eval_steps_per_second": 10.589,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.5709060430526733,
      "learning_rate": 0.0001,
      "loss": 1.757,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 0.787490963935852,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.7692,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 0.7441607117652893,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.8385,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 0.9779700040817261,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.6621,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.96686851978302,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7432,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 1.0333670377731323,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6088,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 0.9446337223052979,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5466,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.6854303479194641,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.2227,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.47890907526016235,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1518,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 0.7436364889144897,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.8991,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.7621960639953613,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6585,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.35844719409942627,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.2974,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 0.3635321259498596,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.644,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.5268105268478394,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5573,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 0.34928566217422485,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5635,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 0.31971651315689087,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6137,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.31752440333366394,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6834,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.27759334444999695,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.5909,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.2512029707431793,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.4532,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 0.27232271432876587,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.1634,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.3015228509902954,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1902,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 0.42352810502052307,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.058,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 0.5410281419754028,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.705,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 0.9533042311668396,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.5321,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "eval_loss": 1.1425410509109497,
      "eval_runtime": 8.6098,
      "eval_samples_per_second": 83.742,
      "eval_steps_per_second": 10.569,
      "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": 5.317548060128051e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}