{
  "best_metric": 1.7293239831924438,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0429553264604811,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "eval_loss": 1.95401132106781,
      "eval_runtime": 27.5604,
      "eval_samples_per_second": 17.779,
      "eval_steps_per_second": 4.463,
      "step": 1
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 0.9405553936958313,
      "learning_rate": 4.36e-05,
      "loss": 1.9074,
      "step": 10
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.0190926790237427,
      "learning_rate": 8.72e-05,
      "loss": 1.6901,
      "step": 20
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 1.3096411228179932,
      "learning_rate": 0.0001308,
      "loss": 1.5987,
      "step": 30
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 1.06441330909729,
      "learning_rate": 0.0001744,
      "loss": 1.5752,
      "step": 40
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 3.1200854778289795,
      "learning_rate": 0.000218,
      "loss": 1.4327,
      "step": 50
    },
    {
      "epoch": 0.0429553264604811,
      "eval_loss": 1.7293239831924438,
      "eval_runtime": 27.5653,
      "eval_samples_per_second": 17.776,
      "eval_steps_per_second": 4.462,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8886804283392000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}