{
  "best_metric": 1.0547163486480713,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.10526315789473684,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 1.1585334539413452,
      "eval_runtime": 1.698,
      "eval_samples_per_second": 23.558,
      "eval_steps_per_second": 11.779,
      "step": 1
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 0.8730560541152954,
      "learning_rate": 6e-05,
      "loss": 4.8303,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 1.1531161069869995,
      "eval_runtime": 1.685,
      "eval_samples_per_second": 23.739,
      "eval_steps_per_second": 11.87,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.0616966485977173,
      "learning_rate": 0.00012,
      "loss": 4.5507,
      "step": 6
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.1517345905303955,
      "learning_rate": 0.00018,
      "loss": 4.4919,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 1.0547163486480713,
      "eval_runtime": 1.6859,
      "eval_samples_per_second": 23.726,
      "eval_steps_per_second": 11.863,
      "step": 10
    }
  ],
  "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": 600937731194880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}