{
  "best_metric": 11.930188179016113,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0028289210023810085,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.429736674603362e-05,
      "eval_loss": 11.93044662475586,
      "eval_runtime": 129.4681,
      "eval_samples_per_second": 34.495,
      "eval_steps_per_second": 17.247,
      "step": 1
    },
    {
      "epoch": 0.00028289210023810083,
      "grad_norm": 0.011236664839088917,
      "learning_rate": 3e-05,
      "loss": 11.93,
      "step": 3
    },
    {
      "epoch": 0.0004714868337301681,
      "eval_loss": 11.930429458618164,
      "eval_runtime": 129.8947,
      "eval_samples_per_second": 34.382,
      "eval_steps_per_second": 17.191,
      "step": 5
    },
    {
      "epoch": 0.0005657842004762017,
      "grad_norm": 0.012191264890134335,
      "learning_rate": 6e-05,
      "loss": 11.9296,
      "step": 6
    },
    {
      "epoch": 0.0008486763007143026,
      "grad_norm": 0.017847776412963867,
      "learning_rate": 9e-05,
      "loss": 11.9309,
      "step": 9
    },
    {
      "epoch": 0.0009429736674603362,
      "eval_loss": 11.930363655090332,
      "eval_runtime": 129.7836,
      "eval_samples_per_second": 34.411,
      "eval_steps_per_second": 17.206,
      "step": 10
    },
    {
      "epoch": 0.0011315684009524033,
      "grad_norm": 0.01458761002868414,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9306,
      "step": 12
    },
    {
      "epoch": 0.0014144605011905042,
      "grad_norm": 0.01205754466354847,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9293,
      "step": 15
    },
    {
      "epoch": 0.0014144605011905042,
      "eval_loss": 11.930285453796387,
      "eval_runtime": 129.4892,
      "eval_samples_per_second": 34.489,
      "eval_steps_per_second": 17.245,
      "step": 15
    },
    {
      "epoch": 0.0016973526014286051,
      "grad_norm": 0.02177605777978897,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.929,
      "step": 18
    },
    {
      "epoch": 0.0018859473349206724,
      "eval_loss": 11.930218696594238,
      "eval_runtime": 129.806,
      "eval_samples_per_second": 34.405,
      "eval_steps_per_second": 17.203,
      "step": 20
    },
    {
      "epoch": 0.001980244701666706,
      "grad_norm": 0.010103181004524231,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 11.9325,
      "step": 21
    },
    {
      "epoch": 0.0022631368019048067,
      "grad_norm": 0.008972418494522572,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9303,
      "step": 24
    },
    {
      "epoch": 0.0023574341686508405,
      "eval_loss": 11.930191040039062,
      "eval_runtime": 129.6099,
      "eval_samples_per_second": 34.457,
      "eval_steps_per_second": 17.229,
      "step": 25
    },
    {
      "epoch": 0.0025460289021429078,
      "grad_norm": 0.016690155491232872,
      "learning_rate": 5.449673790581611e-06,
      "loss": 11.9294,
      "step": 27
    },
    {
      "epoch": 0.0028289210023810085,
      "grad_norm": 0.009384451434016228,
      "learning_rate": 0.0,
      "loss": 11.9296,
      "step": 30
    },
    {
      "epoch": 0.0028289210023810085,
      "eval_loss": 11.930188179016113,
      "eval_runtime": 129.6679,
      "eval_samples_per_second": 34.442,
      "eval_steps_per_second": 17.221,
      "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": 22484090880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}