{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.086387434554974,
  "eval_steps": 25,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08376963350785341,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.08376963350785341,
      "eval_loss": NaN,
      "eval_runtime": 1.85,
      "eval_samples_per_second": 27.027,
      "eval_steps_per_second": 7.027,
      "step": 1
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": NaN,
      "learning_rate": 9.980803793327656e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": NaN,
      "learning_rate": 9.923378948577559e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": NaN,
      "learning_rate": 9.828215394277687e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": NaN,
      "learning_rate": 9.6961250323196e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": NaN,
      "learning_rate": 9.528234811097782e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": NaN,
      "learning_rate": 9.325977110783264e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.7539267015706806,
      "grad_norm": NaN,
      "learning_rate": 9.091077522761079e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": NaN,
      "learning_rate": 8.825540127492967e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.9214659685863874,
      "grad_norm": NaN,
      "learning_rate": 8.531630396409507e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.0287958115183247,
      "grad_norm": NaN,
      "learning_rate": 8.211855863706654e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.112565445026178,
      "grad_norm": NaN,
      "learning_rate": 7.868944732948101e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.1963350785340314,
      "grad_norm": NaN,
      "learning_rate": 7.505822600994424e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.2801047120418847,
      "grad_norm": NaN,
      "learning_rate": 7.12558749784219e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.3638743455497382,
      "grad_norm": NaN,
      "learning_rate": 6.731483455324374e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.4476439790575917,
      "grad_norm": NaN,
      "learning_rate": 6.326872830174567e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.5314136125654452,
      "grad_norm": NaN,
      "learning_rate": 5.9152076175848594e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.6151832460732984,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.6989528795811517,
      "grad_norm": NaN,
      "learning_rate": 5.0847923824151424e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.7827225130890052,
      "grad_norm": NaN,
      "learning_rate": 4.673127169825433e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.8664921465968587,
      "grad_norm": NaN,
      "learning_rate": 4.268516544675628e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.9502617801047122,
      "grad_norm": NaN,
      "learning_rate": 3.8744125021578126e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 2.0575916230366493,
      "grad_norm": NaN,
      "learning_rate": 3.494177399005578e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.141361256544503,
      "grad_norm": NaN,
      "learning_rate": 3.1310552670518986e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.141361256544503,
      "eval_loss": NaN,
      "eval_runtime": 1.7667,
      "eval_samples_per_second": 28.301,
      "eval_steps_per_second": 7.358,
      "step": 25
    },
    {
      "epoch": 2.225130890052356,
      "grad_norm": NaN,
      "learning_rate": 2.7881441362933468e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 2.3089005235602094,
      "grad_norm": NaN,
      "learning_rate": 2.4683696035904928e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 2.392670157068063,
      "grad_norm": NaN,
      "learning_rate": 2.1744598725070347e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 2.4764397905759163,
      "grad_norm": NaN,
      "learning_rate": 1.9089224772389225e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 2.5602094240837694,
      "grad_norm": NaN,
      "learning_rate": 1.674022889216737e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 2.643979057591623,
      "grad_norm": NaN,
      "learning_rate": 1.4717651889022202e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 2.7277486910994764,
      "grad_norm": NaN,
      "learning_rate": 1.3038749676803994e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 2.81151832460733,
      "grad_norm": NaN,
      "learning_rate": 1.1717846057223144e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 2.8952879581151834,
      "grad_norm": NaN,
      "learning_rate": 1.076621051422442e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 3.0026178010471205,
      "grad_norm": NaN,
      "learning_rate": 1.019196206672345e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 3.086387434554974,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 36
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.879899736375296e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}