{
  "best_metric": 1.82761812210083,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0007728423208454895,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.864211604227448e-05,
      "eval_loss": 1.8712239265441895,
      "eval_runtime": 1368.6038,
      "eval_samples_per_second": 7.962,
      "eval_steps_per_second": 3.981,
      "step": 1
    },
    {
      "epoch": 0.00011592634812682343,
      "grad_norm": 8.446324348449707,
      "learning_rate": 6e-05,
      "loss": 17.4809,
      "step": 3
    },
    {
      "epoch": 0.00019321058021137238,
      "eval_loss": 1.867849588394165,
      "eval_runtime": 1373.1927,
      "eval_samples_per_second": 7.936,
      "eval_steps_per_second": 3.968,
      "step": 5
    },
    {
      "epoch": 0.00023185269625364686,
      "grad_norm": 11.185562133789062,
      "learning_rate": 9.96057350657239e-05,
      "loss": 18.1991,
      "step": 6
    },
    {
      "epoch": 0.00034777904438047026,
      "grad_norm": 29.321643829345703,
      "learning_rate": 9.381533400219318e-05,
      "loss": 14.8461,
      "step": 9
    },
    {
      "epoch": 0.00038642116042274477,
      "eval_loss": 1.9294590950012207,
      "eval_runtime": 1373.3106,
      "eval_samples_per_second": 7.935,
      "eval_steps_per_second": 3.968,
      "step": 10
    },
    {
      "epoch": 0.0004637053925072937,
      "grad_norm": 13.129424095153809,
      "learning_rate": 8.18711994874345e-05,
      "loss": 14.6658,
      "step": 12
    },
    {
      "epoch": 0.0005796317406341171,
      "grad_norm": 11.06294059753418,
      "learning_rate": 6.545084971874738e-05,
      "loss": 13.741,
      "step": 15
    },
    {
      "epoch": 0.0005796317406341171,
      "eval_loss": 1.861341953277588,
      "eval_runtime": 1378.0059,
      "eval_samples_per_second": 7.908,
      "eval_steps_per_second": 3.954,
      "step": 15
    },
    {
      "epoch": 0.0006955580887609405,
      "grad_norm": 7.217223167419434,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 13.4053,
      "step": 18
    },
    {
      "epoch": 0.0007728423208454895,
      "eval_loss": 1.82761812210083,
      "eval_runtime": 1378.5654,
      "eval_samples_per_second": 7.905,
      "eval_steps_per_second": 3.953,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5779302566068224.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}