{
  "best_metric": 2.674147367477417,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0023957355906486454,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.985785302162151e-05,
      "eval_loss": 3.2581350803375244,
      "eval_runtime": 664.4084,
      "eval_samples_per_second": 15.871,
      "eval_steps_per_second": 3.969,
      "step": 1
    },
    {
      "epoch": 0.00023957355906486453,
      "grad_norm": 2.439817428588867,
      "learning_rate": 0.00012,
      "loss": 11.3283,
      "step": 3
    },
    {
      "epoch": 0.00039928926510810755,
      "eval_loss": 3.002551317214966,
      "eval_runtime": 666.2754,
      "eval_samples_per_second": 15.827,
      "eval_steps_per_second": 3.958,
      "step": 5
    },
    {
      "epoch": 0.00047914711812972906,
      "grad_norm": 1.635970115661621,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.5552,
      "step": 6
    },
    {
      "epoch": 0.0007187206771945936,
      "grad_norm": 3.0356786251068115,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.4861,
      "step": 9
    },
    {
      "epoch": 0.0007985785302162151,
      "eval_loss": 2.798892021179199,
      "eval_runtime": 666.5496,
      "eval_samples_per_second": 15.82,
      "eval_steps_per_second": 3.956,
      "step": 10
    },
    {
      "epoch": 0.0009582942362594581,
      "grad_norm": 1.8942185640335083,
      "learning_rate": 0.000163742398974869,
      "loss": 11.0834,
      "step": 12
    },
    {
      "epoch": 0.0011978677953243227,
      "grad_norm": 1.716375708580017,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.0553,
      "step": 15
    },
    {
      "epoch": 0.0011978677953243227,
      "eval_loss": 2.712826728820801,
      "eval_runtime": 666.4258,
      "eval_samples_per_second": 15.823,
      "eval_steps_per_second": 3.957,
      "step": 15
    },
    {
      "epoch": 0.0014374413543891873,
      "grad_norm": 1.5416202545166016,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.6655,
      "step": 18
    },
    {
      "epoch": 0.0015971570604324302,
      "eval_loss": 2.6872994899749756,
      "eval_runtime": 666.8046,
      "eval_samples_per_second": 15.814,
      "eval_steps_per_second": 3.955,
      "step": 20
    },
    {
      "epoch": 0.0016770149134540519,
      "grad_norm": 1.627950668334961,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 10.5101,
      "step": 21
    },
    {
      "epoch": 0.0019165884725189162,
      "grad_norm": 1.5547984838485718,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.2943,
      "step": 24
    },
    {
      "epoch": 0.001996446325540538,
      "eval_loss": 2.6766629219055176,
      "eval_runtime": 666.5176,
      "eval_samples_per_second": 15.821,
      "eval_steps_per_second": 3.956,
      "step": 25
    },
    {
      "epoch": 0.002156162031583781,
      "grad_norm": 1.5259841680526733,
      "learning_rate": 7.022351411174866e-06,
      "loss": 10.5363,
      "step": 27
    },
    {
      "epoch": 0.0023957355906486454,
      "grad_norm": 1.845517635345459,
      "learning_rate": 0.0,
      "loss": 10.777,
      "step": 30
    },
    {
      "epoch": 0.0023957355906486454,
      "eval_loss": 2.674147367477417,
      "eval_runtime": 666.9241,
      "eval_samples_per_second": 15.811,
      "eval_steps_per_second": 3.954,
      "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": 3.458910312726528e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}