{
  "best_metric": 1.3134835958480835,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.004243581582855931,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000424358158285593,
      "eval_loss": 1.508124828338623,
      "eval_runtime": 128.6731,
      "eval_samples_per_second": 7.717,
      "eval_steps_per_second": 3.863,
      "step": 1
    },
    {
      "epoch": 0.001273074474856779,
      "grad_norm": 0.5830173492431641,
      "learning_rate": 6e-05,
      "loss": 1.5825,
      "step": 3
    },
    {
      "epoch": 0.0021217907914279654,
      "eval_loss": 1.466567039489746,
      "eval_runtime": 129.6671,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 3.833,
      "step": 5
    },
    {
      "epoch": 0.002546148949713558,
      "grad_norm": 0.5419243574142456,
      "learning_rate": 0.00012,
      "loss": 1.427,
      "step": 6
    },
    {
      "epoch": 0.0038192234245703373,
      "grad_norm": 0.8369843363761902,
      "learning_rate": 0.00018,
      "loss": 1.3801,
      "step": 9
    },
    {
      "epoch": 0.004243581582855931,
      "eval_loss": 1.3134835958480835,
      "eval_runtime": 129.6779,
      "eval_samples_per_second": 7.657,
      "eval_steps_per_second": 3.833,
      "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": 3709436417802240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}