{
  "best_metric": 0.8159880042076111,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7036059806508356,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028144239226033423,
      "grad_norm": 41.251258850097656,
      "learning_rate": 5e-05,
      "loss": 10.8713,
      "step": 1
    },
    {
      "epoch": 0.028144239226033423,
      "eval_loss": 11.611474990844727,
      "eval_runtime": 5.2477,
      "eval_samples_per_second": 9.528,
      "eval_steps_per_second": 2.477,
      "step": 1
    },
    {
      "epoch": 0.056288478452066845,
      "grad_norm": 42.86891555786133,
      "learning_rate": 0.0001,
      "loss": 11.2666,
      "step": 2
    },
    {
      "epoch": 0.08443271767810026,
      "grad_norm": 30.683080673217773,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.4065,
      "step": 3
    },
    {
      "epoch": 0.11257695690413369,
      "grad_norm": 17.567529678344727,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.7922,
      "step": 4
    },
    {
      "epoch": 0.14072119613016712,
      "grad_norm": 10.173680305480957,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.0552,
      "step": 5
    },
    {
      "epoch": 0.16886543535620052,
      "grad_norm": 4.438224792480469,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.3103,
      "step": 6
    },
    {
      "epoch": 0.19700967458223395,
      "grad_norm": 3.33147931098938,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.0359,
      "step": 7
    },
    {
      "epoch": 0.22515391380826738,
      "grad_norm": 2.65921688079834,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.0297,
      "step": 8
    },
    {
      "epoch": 0.2532981530343008,
      "grad_norm": 1.5921533107757568,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.9496,
      "step": 9
    },
    {
      "epoch": 0.28144239226033424,
      "grad_norm": 2.4922847747802734,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.8046,
      "step": 10
    },
    {
      "epoch": 0.3095866314863676,
      "grad_norm": 1.0983978509902954,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.7705,
      "step": 11
    },
    {
      "epoch": 0.33773087071240104,
      "grad_norm": 0.9080610871315002,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.8037,
      "step": 12
    },
    {
      "epoch": 0.3658751099384345,
      "grad_norm": 0.7231888175010681,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.7878,
      "step": 13
    },
    {
      "epoch": 0.3940193491644679,
      "grad_norm": 0.5231512784957886,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.7821,
      "step": 14
    },
    {
      "epoch": 0.42216358839050133,
      "grad_norm": 0.5364855527877808,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.8491,
      "step": 15
    },
    {
      "epoch": 0.45030782761653476,
      "grad_norm": 0.7105052471160889,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.803,
      "step": 16
    },
    {
      "epoch": 0.47845206684256814,
      "grad_norm": 0.5208602547645569,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.8514,
      "step": 17
    },
    {
      "epoch": 0.5065963060686016,
      "grad_norm": 0.7129954099655151,
      "learning_rate": 7.75e-05,
      "loss": 0.7448,
      "step": 18
    },
    {
      "epoch": 0.534740545294635,
      "grad_norm": 0.45417389273643494,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.7259,
      "step": 19
    },
    {
      "epoch": 0.5628847845206685,
      "grad_norm": 0.29068127274513245,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.7371,
      "step": 20
    },
    {
      "epoch": 0.5910290237467019,
      "grad_norm": 0.7438077926635742,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.776,
      "step": 21
    },
    {
      "epoch": 0.6191732629727352,
      "grad_norm": 0.5736115574836731,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.7734,
      "step": 22
    },
    {
      "epoch": 0.6473175021987687,
      "grad_norm": 0.9464084506034851,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.8445,
      "step": 23
    },
    {
      "epoch": 0.6754617414248021,
      "grad_norm": 0.3483090102672577,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.7999,
      "step": 24
    },
    {
      "epoch": 0.7036059806508356,
      "grad_norm": 0.36117613315582275,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.8521,
      "step": 25
    },
    {
      "epoch": 0.7036059806508356,
      "eval_loss": 0.8159880042076111,
      "eval_runtime": 5.0985,
      "eval_samples_per_second": 9.807,
      "eval_steps_per_second": 2.55,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.315690861756416e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}