{
  "best_metric": 1.7913482189178467,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0032665060634518802,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016332530317259402,
      "grad_norm": 9.467520713806152,
      "learning_rate": 2e-05,
      "loss": 21.3491,
      "step": 1
    },
    {
      "epoch": 0.00016332530317259402,
      "eval_loss": 1.7752217054367065,
      "eval_runtime": 348.2714,
      "eval_samples_per_second": 7.402,
      "eval_steps_per_second": 3.701,
      "step": 1
    },
    {
      "epoch": 0.00032665060634518803,
      "grad_norm": 9.020357131958008,
      "learning_rate": 4e-05,
      "loss": 15.3594,
      "step": 2
    },
    {
      "epoch": 0.0004899759095177821,
      "grad_norm": 8.410806655883789,
      "learning_rate": 6e-05,
      "loss": 16.5062,
      "step": 3
    },
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 68.47444152832031,
      "learning_rate": 8e-05,
      "loss": 19.5322,
      "step": 4
    },
    {
      "epoch": 0.0008166265158629701,
      "grad_norm": 8.83053970336914,
      "learning_rate": 0.0001,
      "loss": 20.2128,
      "step": 5
    },
    {
      "epoch": 0.0008166265158629701,
      "eval_loss": 1.7732576131820679,
      "eval_runtime": 344.6987,
      "eval_samples_per_second": 7.479,
      "eval_steps_per_second": 3.739,
      "step": 5
    },
    {
      "epoch": 0.0009799518190355642,
      "grad_norm": 158.2658233642578,
      "learning_rate": 0.00012,
      "loss": 18.7829,
      "step": 6
    },
    {
      "epoch": 0.0011432771222081581,
      "grad_norm": 14.250526428222656,
      "learning_rate": 0.00014,
      "loss": 22.2495,
      "step": 7
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 39.55696105957031,
      "learning_rate": 0.00016,
      "loss": 18.8235,
      "step": 8
    },
    {
      "epoch": 0.0014699277285533461,
      "grad_norm": 18.592853546142578,
      "learning_rate": 0.00018,
      "loss": 19.2488,
      "step": 9
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 11.370742797851562,
      "learning_rate": 0.0002,
      "loss": 16.3552,
      "step": 10
    },
    {
      "epoch": 0.0016332530317259401,
      "eval_loss": 1.7994377613067627,
      "eval_runtime": 345.405,
      "eval_samples_per_second": 7.464,
      "eval_steps_per_second": 3.732,
      "step": 10
    },
    {
      "epoch": 0.001796578334898534,
      "grad_norm": 11.962382316589355,
      "learning_rate": 0.00019781476007338058,
      "loss": 18.0219,
      "step": 11
    },
    {
      "epoch": 0.0019599036380711283,
      "grad_norm": 19.99713134765625,
      "learning_rate": 0.0001913545457642601,
      "loss": 14.4894,
      "step": 12
    },
    {
      "epoch": 0.0021232289412437223,
      "grad_norm": 18.155807495117188,
      "learning_rate": 0.00018090169943749476,
      "loss": 12.3312,
      "step": 13
    },
    {
      "epoch": 0.0022865542444163163,
      "grad_norm": 16.805404663085938,
      "learning_rate": 0.00016691306063588583,
      "loss": 12.8574,
      "step": 14
    },
    {
      "epoch": 0.0024498795475889103,
      "grad_norm": 75.45690155029297,
      "learning_rate": 0.00015000000000000001,
      "loss": 12.9431,
      "step": 15
    },
    {
      "epoch": 0.0024498795475889103,
      "eval_loss": 1.813950777053833,
      "eval_runtime": 347.2825,
      "eval_samples_per_second": 7.423,
      "eval_steps_per_second": 3.712,
      "step": 15
    },
    {
      "epoch": 0.0026132048507615043,
      "grad_norm": 17.49741554260254,
      "learning_rate": 0.00013090169943749476,
      "loss": 16.0895,
      "step": 16
    },
    {
      "epoch": 0.0027765301539340983,
      "grad_norm": 21.23000717163086,
      "learning_rate": 0.00011045284632676536,
      "loss": 15.8599,
      "step": 17
    },
    {
      "epoch": 0.0029398554571066922,
      "grad_norm": 11.388646125793457,
      "learning_rate": 8.954715367323468e-05,
      "loss": 14.4246,
      "step": 18
    },
    {
      "epoch": 0.0031031807602792862,
      "grad_norm": 14.265610694885254,
      "learning_rate": 6.909830056250527e-05,
      "loss": 13.915,
      "step": 19
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 16.39878273010254,
      "learning_rate": 5.000000000000002e-05,
      "loss": 12.9095,
      "step": 20
    },
    {
      "epoch": 0.0032665060634518802,
      "eval_loss": 1.7913482189178467,
      "eval_runtime": 346.068,
      "eval_samples_per_second": 7.449,
      "eval_steps_per_second": 3.725,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 2167222768238592.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}