{
  "best_metric": 0.3640096187591553,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.013723696248856358,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004574565416285453,
      "eval_loss": 1.9771651029586792,
      "eval_runtime": 162.2414,
      "eval_samples_per_second": 11.347,
      "eval_steps_per_second": 2.841,
      "step": 1
    },
    {
      "epoch": 0.0013723696248856359,
      "grad_norm": 2.4774668216705322,
      "learning_rate": 0.00012,
      "loss": 1.5771,
      "step": 3
    },
    {
      "epoch": 0.0022872827081427266,
      "eval_loss": 1.0017728805541992,
      "eval_runtime": 162.3692,
      "eval_samples_per_second": 11.338,
      "eval_steps_per_second": 2.839,
      "step": 5
    },
    {
      "epoch": 0.0027447392497712718,
      "grad_norm": 1.7279980182647705,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.1196,
      "step": 6
    },
    {
      "epoch": 0.004117108874656907,
      "grad_norm": 0.7745809555053711,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.6265,
      "step": 9
    },
    {
      "epoch": 0.004574565416285453,
      "eval_loss": 0.4537348747253418,
      "eval_runtime": 162.3245,
      "eval_samples_per_second": 11.341,
      "eval_steps_per_second": 2.84,
      "step": 10
    },
    {
      "epoch": 0.0054894784995425435,
      "grad_norm": 0.5128909945487976,
      "learning_rate": 0.000163742398974869,
      "loss": 0.4514,
      "step": 12
    },
    {
      "epoch": 0.006861848124428179,
      "grad_norm": 0.47929856181144714,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.4212,
      "step": 15
    },
    {
      "epoch": 0.006861848124428179,
      "eval_loss": 0.39974135160446167,
      "eval_runtime": 162.3452,
      "eval_samples_per_second": 11.34,
      "eval_steps_per_second": 2.84,
      "step": 15
    },
    {
      "epoch": 0.008234217749313814,
      "grad_norm": 0.5202671885490417,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.3923,
      "step": 18
    },
    {
      "epoch": 0.009149130832570906,
      "eval_loss": 0.3763931095600128,
      "eval_runtime": 162.4133,
      "eval_samples_per_second": 11.335,
      "eval_steps_per_second": 2.838,
      "step": 20
    },
    {
      "epoch": 0.00960658737419945,
      "grad_norm": 0.35927730798721313,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.3669,
      "step": 21
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 0.31829825043678284,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.3661,
      "step": 24
    },
    {
      "epoch": 0.011436413540713633,
      "eval_loss": 0.36795511841773987,
      "eval_runtime": 162.5768,
      "eval_samples_per_second": 11.324,
      "eval_steps_per_second": 2.836,
      "step": 25
    },
    {
      "epoch": 0.012351326623970723,
      "grad_norm": 0.40827932953834534,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.3549,
      "step": 27
    },
    {
      "epoch": 0.013723696248856358,
      "grad_norm": 0.34633514285087585,
      "learning_rate": 0.0,
      "loss": 0.3407,
      "step": 30
    },
    {
      "epoch": 0.013723696248856358,
      "eval_loss": 0.3640096187591553,
      "eval_runtime": 162.3702,
      "eval_samples_per_second": 11.338,
      "eval_steps_per_second": 2.839,
      "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": 2.470837626077184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}