{
  "best_metric": 0.3052322566509247,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1554605518849592,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006218422075398368,
      "grad_norm": 0.22229772806167603,
      "learning_rate": 5e-05,
      "loss": 0.3638,
      "step": 1
    },
    {
      "epoch": 0.006218422075398368,
      "eval_loss": 0.6265063285827637,
      "eval_runtime": 1.401,
      "eval_samples_per_second": 35.689,
      "eval_steps_per_second": 9.279,
      "step": 1
    },
    {
      "epoch": 0.012436844150796735,
      "grad_norm": 0.34933504462242126,
      "learning_rate": 0.0001,
      "loss": 0.4261,
      "step": 2
    },
    {
      "epoch": 0.018655266226195105,
      "grad_norm": 0.3780006766319275,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.3986,
      "step": 3
    },
    {
      "epoch": 0.02487368830159347,
      "grad_norm": 0.3268946707248688,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.3963,
      "step": 4
    },
    {
      "epoch": 0.03109211037699184,
      "grad_norm": 0.36501720547676086,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.3709,
      "step": 5
    },
    {
      "epoch": 0.03731053245239021,
      "grad_norm": 0.3809024691581726,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.3323,
      "step": 6
    },
    {
      "epoch": 0.04352895452778857,
      "grad_norm": 0.3877021074295044,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.3416,
      "step": 7
    },
    {
      "epoch": 0.04974737660318694,
      "grad_norm": 0.29683631658554077,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.3326,
      "step": 8
    },
    {
      "epoch": 0.05596579867858531,
      "grad_norm": 0.49793848395347595,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.3584,
      "step": 9
    },
    {
      "epoch": 0.06218422075398368,
      "grad_norm": 0.4865315854549408,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.3416,
      "step": 10
    },
    {
      "epoch": 0.06840264282938205,
      "grad_norm": 0.5153951048851013,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.4089,
      "step": 11
    },
    {
      "epoch": 0.07462106490478042,
      "grad_norm": 0.45801788568496704,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.4065,
      "step": 12
    },
    {
      "epoch": 0.08083948698017877,
      "grad_norm": 0.09606501460075378,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.3175,
      "step": 13
    },
    {
      "epoch": 0.08705790905557714,
      "grad_norm": 0.12753839790821075,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.315,
      "step": 14
    },
    {
      "epoch": 0.09327633113097551,
      "grad_norm": 0.2014089673757553,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.3216,
      "step": 15
    },
    {
      "epoch": 0.09949475320637388,
      "grad_norm": 0.1620405614376068,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.282,
      "step": 16
    },
    {
      "epoch": 0.10571317528177225,
      "grad_norm": 0.12604041397571564,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.2787,
      "step": 17
    },
    {
      "epoch": 0.11193159735717062,
      "grad_norm": 0.1285071223974228,
      "learning_rate": 7.75e-05,
      "loss": 0.2843,
      "step": 18
    },
    {
      "epoch": 0.11815001943256899,
      "grad_norm": 0.10579027980566025,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.28,
      "step": 19
    },
    {
      "epoch": 0.12436844150796736,
      "grad_norm": 0.13292458653450012,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.2943,
      "step": 20
    },
    {
      "epoch": 0.13058686358336571,
      "grad_norm": 0.11772623658180237,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.268,
      "step": 21
    },
    {
      "epoch": 0.1368052856587641,
      "grad_norm": 0.1446559578180313,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.3321,
      "step": 22
    },
    {
      "epoch": 0.14302370773416245,
      "grad_norm": 0.18193776905536652,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.3311,
      "step": 23
    },
    {
      "epoch": 0.14924212980956084,
      "grad_norm": 0.22447001934051514,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.3661,
      "step": 24
    },
    {
      "epoch": 0.1554605518849592,
      "grad_norm": 0.45850419998168945,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.3917,
      "step": 25
    },
    {
      "epoch": 0.1554605518849592,
      "eval_loss": 0.3052322566509247,
      "eval_runtime": 0.6619,
      "eval_samples_per_second": 75.543,
      "eval_steps_per_second": 19.641,
      "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": 5.310925972176896e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}