{
  "best_metric": 1.1891251802444458,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.036596523330283626,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 2.5816187858581543,
      "eval_runtime": 26.9741,
      "eval_samples_per_second": 4.263,
      "eval_steps_per_second": 2.15,
      "step": 1
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 1.2698482275009155,
      "learning_rate": 6e-05,
      "loss": 2.6578,
      "step": 3
    },
    {
      "epoch": 0.018298261665141813,
      "eval_loss": 2.296178102493286,
      "eval_runtime": 26.9636,
      "eval_samples_per_second": 4.265,
      "eval_steps_per_second": 2.151,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 1.6247072219848633,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.48,
      "step": 6
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 2.1021180152893066,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.8493,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 1.1891251802444458,
      "eval_runtime": 27.1091,
      "eval_samples_per_second": 4.242,
      "eval_steps_per_second": 2.14,
      "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": 3305470584422400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}