{
  "best_metric": 1.4364030361175537,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0332944897619444,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001331779590477776,
      "grad_norm": 1.716598391532898,
      "learning_rate": 5e-05,
      "loss": 2.2224,
      "step": 1
    },
    {
      "epoch": 0.001331779590477776,
      "eval_loss": 2.8852221965789795,
      "eval_runtime": 133.4508,
      "eval_samples_per_second": 37.909,
      "eval_steps_per_second": 4.743,
      "step": 1
    },
    {
      "epoch": 0.002663559180955552,
      "grad_norm": 1.9544339179992676,
      "learning_rate": 0.0001,
      "loss": 2.3534,
      "step": 2
    },
    {
      "epoch": 0.003995338771433328,
      "grad_norm": 1.9382542371749878,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.315,
      "step": 3
    },
    {
      "epoch": 0.005327118361911104,
      "grad_norm": 1.8056589365005493,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.223,
      "step": 4
    },
    {
      "epoch": 0.00665889795238888,
      "grad_norm": 1.8618559837341309,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.094,
      "step": 5
    },
    {
      "epoch": 0.007990677542866656,
      "grad_norm": 1.720023512840271,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9048,
      "step": 6
    },
    {
      "epoch": 0.009322457133344432,
      "grad_norm": 1.8842785358428955,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.7269,
      "step": 7
    },
    {
      "epoch": 0.010654236723822208,
      "grad_norm": 1.7412643432617188,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7371,
      "step": 8
    },
    {
      "epoch": 0.011986016314299984,
      "grad_norm": 2.0039165019989014,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6742,
      "step": 9
    },
    {
      "epoch": 0.01331779590477776,
      "grad_norm": 1.7889673709869385,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5504,
      "step": 10
    },
    {
      "epoch": 0.014649575495255536,
      "grad_norm": 1.569449782371521,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.4855,
      "step": 11
    },
    {
      "epoch": 0.015981355085733312,
      "grad_norm": 1.9054864645004272,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5665,
      "step": 12
    },
    {
      "epoch": 0.017313134676211088,
      "grad_norm": 1.3979929685592651,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.8186,
      "step": 13
    },
    {
      "epoch": 0.018644914266688864,
      "grad_norm": 0.9748731255531311,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6544,
      "step": 14
    },
    {
      "epoch": 0.01997669385716664,
      "grad_norm": 0.8066844344139099,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5756,
      "step": 15
    },
    {
      "epoch": 0.021308473447644416,
      "grad_norm": 0.7804756164550781,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6058,
      "step": 16
    },
    {
      "epoch": 0.022640253038122192,
      "grad_norm": 0.7928308248519897,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.3039,
      "step": 17
    },
    {
      "epoch": 0.023972032628599968,
      "grad_norm": 0.8666258454322815,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3077,
      "step": 18
    },
    {
      "epoch": 0.025303812219077744,
      "grad_norm": 0.960999608039856,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.4093,
      "step": 19
    },
    {
      "epoch": 0.02663559180955552,
      "grad_norm": 1.0699888467788696,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.357,
      "step": 20
    },
    {
      "epoch": 0.027967371400033296,
      "grad_norm": 1.1570630073547363,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.4088,
      "step": 21
    },
    {
      "epoch": 0.029299150990511072,
      "grad_norm": 1.1443278789520264,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.3868,
      "step": 22
    },
    {
      "epoch": 0.030630930580988848,
      "grad_norm": 1.2050145864486694,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.3297,
      "step": 23
    },
    {
      "epoch": 0.031962710171466624,
      "grad_norm": 1.2424426078796387,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1877,
      "step": 24
    },
    {
      "epoch": 0.0332944897619444,
      "grad_norm": 1.9407079219818115,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5371,
      "step": 25
    },
    {
      "epoch": 0.0332944897619444,
      "eval_loss": 1.4364030361175537,
      "eval_runtime": 132.66,
      "eval_samples_per_second": 38.135,
      "eval_steps_per_second": 4.772,
      "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}