{
  "best_metric": 0.9166544079780579,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.12543116964565695,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005017246785826278,
      "grad_norm": 9.703303337097168,
      "learning_rate": 5e-05,
      "loss": 20.3254,
      "step": 1
    },
    {
      "epoch": 0.005017246785826278,
      "eval_loss": 1.2978161573410034,
      "eval_runtime": 4.7129,
      "eval_samples_per_second": 10.609,
      "eval_steps_per_second": 2.758,
      "step": 1
    },
    {
      "epoch": 0.010034493571652555,
      "grad_norm": 9.683317184448242,
      "learning_rate": 0.0001,
      "loss": 21.204,
      "step": 2
    },
    {
      "epoch": 0.015051740357478834,
      "grad_norm": 9.175610542297363,
      "learning_rate": 9.990365154573717e-05,
      "loss": 21.2752,
      "step": 3
    },
    {
      "epoch": 0.02006898714330511,
      "grad_norm": 7.235718727111816,
      "learning_rate": 9.961501876182148e-05,
      "loss": 20.5861,
      "step": 4
    },
    {
      "epoch": 0.02508623392913139,
      "grad_norm": 5.989271640777588,
      "learning_rate": 9.913533761814537e-05,
      "loss": 20.3062,
      "step": 5
    },
    {
      "epoch": 0.030103480714957668,
      "grad_norm": 5.9048943519592285,
      "learning_rate": 9.846666218300807e-05,
      "loss": 16.6151,
      "step": 6
    },
    {
      "epoch": 0.035120727500783946,
      "grad_norm": 5.446622848510742,
      "learning_rate": 9.761185582727977e-05,
      "loss": 15.4788,
      "step": 7
    },
    {
      "epoch": 0.04013797428661022,
      "grad_norm": 4.205174922943115,
      "learning_rate": 9.657457896300791e-05,
      "loss": 14.4654,
      "step": 8
    },
    {
      "epoch": 0.045155221072436504,
      "grad_norm": 4.592187404632568,
      "learning_rate": 9.535927336897098e-05,
      "loss": 14.5299,
      "step": 9
    },
    {
      "epoch": 0.05017246785826278,
      "grad_norm": 4.325466632843018,
      "learning_rate": 9.397114317029975e-05,
      "loss": 14.6725,
      "step": 10
    },
    {
      "epoch": 0.055189714644089054,
      "grad_norm": 5.832132816314697,
      "learning_rate": 9.241613255361455e-05,
      "loss": 14.7624,
      "step": 11
    },
    {
      "epoch": 0.060206961429915336,
      "grad_norm": 4.706078052520752,
      "learning_rate": 9.070090031310558e-05,
      "loss": 14.8782,
      "step": 12
    },
    {
      "epoch": 0.06522420821574161,
      "grad_norm": 6.7769036293029785,
      "learning_rate": 8.883279133655399e-05,
      "loss": 15.411,
      "step": 13
    },
    {
      "epoch": 0.07024145500156789,
      "grad_norm": 8.079216003417969,
      "learning_rate": 8.681980515339464e-05,
      "loss": 16.0098,
      "step": 14
    },
    {
      "epoch": 0.07525870178739416,
      "grad_norm": 6.023728847503662,
      "learning_rate": 8.467056167950311e-05,
      "loss": 16.1647,
      "step": 15
    },
    {
      "epoch": 0.08027594857322044,
      "grad_norm": 5.478669166564941,
      "learning_rate": 8.239426430539243e-05,
      "loss": 16.0336,
      "step": 16
    },
    {
      "epoch": 0.08529319535904673,
      "grad_norm": 8.347612380981445,
      "learning_rate": 8.000066048588211e-05,
      "loss": 15.9954,
      "step": 17
    },
    {
      "epoch": 0.09031044214487301,
      "grad_norm": 4.436486721038818,
      "learning_rate": 7.75e-05,
      "loss": 16.4564,
      "step": 18
    },
    {
      "epoch": 0.09532768893069928,
      "grad_norm": 3.357234477996826,
      "learning_rate": 7.490299105985507e-05,
      "loss": 14.9274,
      "step": 19
    },
    {
      "epoch": 0.10034493571652556,
      "grad_norm": 3.9774246215820312,
      "learning_rate": 7.222075445642904e-05,
      "loss": 13.62,
      "step": 20
    },
    {
      "epoch": 0.10536218250235184,
      "grad_norm": 3.324450969696045,
      "learning_rate": 6.946477593864228e-05,
      "loss": 12.903,
      "step": 21
    },
    {
      "epoch": 0.11037942928817811,
      "grad_norm": 2.9704174995422363,
      "learning_rate": 6.664685702961344e-05,
      "loss": 12.8763,
      "step": 22
    },
    {
      "epoch": 0.11539667607400439,
      "grad_norm": 3.2032809257507324,
      "learning_rate": 6.377906449072578e-05,
      "loss": 13.639,
      "step": 23
    },
    {
      "epoch": 0.12041392285983067,
      "grad_norm": 3.6382336616516113,
      "learning_rate": 6.087367864990233e-05,
      "loss": 13.5673,
      "step": 24
    },
    {
      "epoch": 0.12543116964565695,
      "grad_norm": 4.114265441894531,
      "learning_rate": 5.794314081535644e-05,
      "loss": 14.5865,
      "step": 25
    },
    {
      "epoch": 0.12543116964565695,
      "eval_loss": 0.9166544079780579,
      "eval_runtime": 4.5965,
      "eval_samples_per_second": 10.878,
      "eval_steps_per_second": 2.828,
      "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": 3.949258989581107e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}