{
  "best_metric": 2.1525070667266846,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0015880788216455144,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.2935960721517145e-05,
      "eval_loss": 2.296342134475708,
      "eval_runtime": 1097.2858,
      "eval_samples_per_second": 14.498,
      "eval_steps_per_second": 3.624,
      "step": 1
    },
    {
      "epoch": 0.00015880788216455144,
      "grad_norm": 0.37316057085990906,
      "learning_rate": 0.00012,
      "loss": 2.4888,
      "step": 3
    },
    {
      "epoch": 0.0002646798036075857,
      "eval_loss": 2.258819580078125,
      "eval_runtime": 1105.3703,
      "eval_samples_per_second": 14.392,
      "eval_steps_per_second": 3.598,
      "step": 5
    },
    {
      "epoch": 0.00031761576432910287,
      "grad_norm": 0.3321237564086914,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2427,
      "step": 6
    },
    {
      "epoch": 0.0004764236464936543,
      "grad_norm": 0.36119964718818665,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.1671,
      "step": 9
    },
    {
      "epoch": 0.0005293596072151715,
      "eval_loss": 2.200221300125122,
      "eval_runtime": 1104.1978,
      "eval_samples_per_second": 14.407,
      "eval_steps_per_second": 3.602,
      "step": 10
    },
    {
      "epoch": 0.0006352315286582057,
      "grad_norm": 0.37875980138778687,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2376,
      "step": 12
    },
    {
      "epoch": 0.0007940394108227572,
      "grad_norm": 0.3475739359855652,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2848,
      "step": 15
    },
    {
      "epoch": 0.0007940394108227572,
      "eval_loss": 2.1903977394104004,
      "eval_runtime": 1105.3461,
      "eval_samples_per_second": 14.392,
      "eval_steps_per_second": 3.598,
      "step": 15
    },
    {
      "epoch": 0.0009528472929873086,
      "grad_norm": 0.36161014437675476,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.2015,
      "step": 18
    },
    {
      "epoch": 0.001058719214430343,
      "eval_loss": 2.169541120529175,
      "eval_runtime": 1104.0874,
      "eval_samples_per_second": 14.408,
      "eval_steps_per_second": 3.602,
      "step": 20
    },
    {
      "epoch": 0.00111165517515186,
      "grad_norm": 0.3320382535457611,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.208,
      "step": 21
    },
    {
      "epoch": 0.0012704630573164115,
      "grad_norm": 0.3757071793079376,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.1393,
      "step": 24
    },
    {
      "epoch": 0.0013233990180379286,
      "eval_loss": 2.1603212356567383,
      "eval_runtime": 1101.2407,
      "eval_samples_per_second": 14.446,
      "eval_steps_per_second": 3.611,
      "step": 25
    },
    {
      "epoch": 0.001429270939480963,
      "grad_norm": 0.4626060426235199,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.0964,
      "step": 27
    },
    {
      "epoch": 0.0015880788216455144,
      "grad_norm": 0.5889630317687988,
      "learning_rate": 0.0,
      "loss": 2.1956,
      "step": 30
    },
    {
      "epoch": 0.0015880788216455144,
      "eval_loss": 2.1525070667266846,
      "eval_runtime": 1102.4068,
      "eval_samples_per_second": 14.43,
      "eval_steps_per_second": 3.608,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8340346962444288.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}