{
  "best_metric": 10.373156547546387,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02577873254564984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 10.374519348144531,
      "eval_runtime": 2.3511,
      "eval_samples_per_second": 208.416,
      "eval_steps_per_second": 104.208,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.025225499644875526,
      "learning_rate": 6e-05,
      "loss": 10.371,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 10.374321937561035,
      "eval_runtime": 2.4214,
      "eval_samples_per_second": 202.363,
      "eval_steps_per_second": 101.181,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.130941703915596,
      "learning_rate": 9.96057350657239e-05,
      "loss": 10.374,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.05881809443235397,
      "learning_rate": 9.381533400219318e-05,
      "loss": 10.3736,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 10.373871803283691,
      "eval_runtime": 2.3931,
      "eval_samples_per_second": 204.758,
      "eval_steps_per_second": 102.379,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 0.02660459280014038,
      "learning_rate": 8.18711994874345e-05,
      "loss": 10.3789,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.039102476090192795,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3746,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 10.373516082763672,
      "eval_runtime": 2.3838,
      "eval_samples_per_second": 205.553,
      "eval_steps_per_second": 102.776,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 0.037715379148721695,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 10.374,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 10.373284339904785,
      "eval_runtime": 2.3875,
      "eval_samples_per_second": 205.237,
      "eval_steps_per_second": 102.618,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 0.028755083680152893,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 10.3772,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.08036826550960541,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 10.3762,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 10.373167991638184,
      "eval_runtime": 2.4205,
      "eval_samples_per_second": 202.435,
      "eval_steps_per_second": 101.217,
      "step": 25
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 0.11728760600090027,
      "learning_rate": 3.511175705587433e-06,
      "loss": 10.3719,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.03800259530544281,
      "learning_rate": 0.0,
      "loss": 10.3755,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 10.373156547546387,
      "eval_runtime": 2.4447,
      "eval_samples_per_second": 200.433,
      "eval_steps_per_second": 100.217,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 797612310528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}