{
  "best_metric": 1.3357820510864258,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.08009771921744528,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016019543843489057,
      "eval_loss": 1.5391645431518555,
      "eval_runtime": 1135.6547,
      "eval_samples_per_second": 9.258,
      "eval_steps_per_second": 2.315,
      "step": 1
    },
    {
      "epoch": 0.008009771921744529,
      "grad_norm": 15.790509223937988,
      "learning_rate": 0.000106,
      "loss": 10.4315,
      "step": 50
    },
    {
      "epoch": 0.016019543843489057,
      "grad_norm": 18.460023880004883,
      "learning_rate": 0.000212,
      "loss": 10.5652,
      "step": 100
    },
    {
      "epoch": 0.024029315765233584,
      "grad_norm": 19.40390968322754,
      "learning_rate": 0.0002039312304461964,
      "loss": 10.8745,
      "step": 150
    },
    {
      "epoch": 0.032039087686978114,
      "grad_norm": 20.609119415283203,
      "learning_rate": 0.00018095331880577404,
      "loss": 11.2246,
      "step": 200
    },
    {
      "epoch": 0.04004885960872264,
      "grad_norm": 18.397924423217773,
      "learning_rate": 0.00014656444383069953,
      "loss": 11.2315,
      "step": 250
    },
    {
      "epoch": 0.04805863153046717,
      "grad_norm": 20.244464874267578,
      "learning_rate": 0.000106,
      "loss": 10.9867,
      "step": 300
    },
    {
      "epoch": 0.0560684034522117,
      "grad_norm": 18.18651008605957,
      "learning_rate": 6.543555616930049e-05,
      "loss": 10.9874,
      "step": 350
    },
    {
      "epoch": 0.06407817537395623,
      "grad_norm": 17.651397705078125,
      "learning_rate": 3.104668119422597e-05,
      "loss": 10.8625,
      "step": 400
    },
    {
      "epoch": 0.07208794729570075,
      "grad_norm": 18.79920768737793,
      "learning_rate": 8.068769553803605e-06,
      "loss": 10.7304,
      "step": 450
    },
    {
      "epoch": 0.08009771921744528,
      "grad_norm": 18.035497665405273,
      "learning_rate": 0.0,
      "loss": 10.622,
      "step": 500
    },
    {
      "epoch": 0.08009771921744528,
      "eval_loss": 1.3357820510864258,
      "eval_runtime": 1135.8025,
      "eval_samples_per_second": 9.257,
      "eval_steps_per_second": 2.315,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 7.196131237696635e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}