{
  "best_metric": 2.293621778488159,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0008618275052248292,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.618275052248293e-05,
      "eval_loss": 2.57096529006958,
      "eval_runtime": 724.3902,
      "eval_samples_per_second": 6.745,
      "eval_steps_per_second": 3.372,
      "step": 1
    },
    {
      "epoch": 0.0002585482515674488,
      "grad_norm": 1.1678370237350464,
      "learning_rate": 3e-05,
      "loss": 2.5973,
      "step": 3
    },
    {
      "epoch": 0.0004309137526124146,
      "eval_loss": 2.531855344772339,
      "eval_runtime": 727.2568,
      "eval_samples_per_second": 6.718,
      "eval_steps_per_second": 3.359,
      "step": 5
    },
    {
      "epoch": 0.0005170965031348976,
      "grad_norm": 0.9036294221878052,
      "learning_rate": 6e-05,
      "loss": 2.6077,
      "step": 6
    },
    {
      "epoch": 0.0007756447547023463,
      "grad_norm": 0.9021340608596802,
      "learning_rate": 9e-05,
      "loss": 2.5392,
      "step": 9
    },
    {
      "epoch": 0.0008618275052248292,
      "eval_loss": 2.293621778488159,
      "eval_runtime": 727.6181,
      "eval_samples_per_second": 6.715,
      "eval_steps_per_second": 3.358,
      "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": 1852139254579200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}