{
  "best_metric": 1.3492194414138794,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.3380376912025691,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006760753824051382,
      "eval_loss": 1.767673373222351,
      "eval_runtime": 338.9787,
      "eval_samples_per_second": 7.349,
      "eval_steps_per_second": 1.838,
      "step": 1
    },
    {
      "epoch": 0.033803769120256906,
      "grad_norm": 1.7790162563323975,
      "learning_rate": 0.000106,
      "loss": 1.5289,
      "step": 50
    },
    {
      "epoch": 0.06760753824051381,
      "grad_norm": 1.7413740158081055,
      "learning_rate": 0.000212,
      "loss": 1.413,
      "step": 100
    },
    {
      "epoch": 0.10141130736077072,
      "grad_norm": 1.6365270614624023,
      "learning_rate": 0.0002039312304461964,
      "loss": 1.4142,
      "step": 150
    },
    {
      "epoch": 0.13521507648102762,
      "grad_norm": 2.3726978302001953,
      "learning_rate": 0.00018095331880577404,
      "loss": 1.4116,
      "step": 200
    },
    {
      "epoch": 0.16901884560128455,
      "grad_norm": 1.5051225423812866,
      "learning_rate": 0.00014656444383069953,
      "loss": 1.4009,
      "step": 250
    },
    {
      "epoch": 0.20282261472154145,
      "grad_norm": 1.5823427438735962,
      "learning_rate": 0.000106,
      "loss": 1.3708,
      "step": 300
    },
    {
      "epoch": 0.23662638384179835,
      "grad_norm": 1.1779499053955078,
      "learning_rate": 6.543555616930049e-05,
      "loss": 1.3753,
      "step": 350
    },
    {
      "epoch": 0.27043015296205525,
      "grad_norm": 1.2293542623519897,
      "learning_rate": 3.104668119422597e-05,
      "loss": 1.3557,
      "step": 400
    },
    {
      "epoch": 0.3042339220823122,
      "grad_norm": 1.7364064455032349,
      "learning_rate": 8.068769553803605e-06,
      "loss": 1.3373,
      "step": 450
    },
    {
      "epoch": 0.3380376912025691,
      "grad_norm": 1.5903881788253784,
      "learning_rate": 0.0,
      "loss": 1.3504,
      "step": 500
    },
    {
      "epoch": 0.3380376912025691,
      "eval_loss": 1.3492194414138794,
      "eval_runtime": 340.0991,
      "eval_samples_per_second": 7.324,
      "eval_steps_per_second": 1.832,
      "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": 9.411239089400709e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}