{
  "best_metric": 1.8055723905563354,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "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": 6.833710193634033,
      "learning_rate": 2e-05,
      "loss": 17.2541,
      "step": 1
    },
    {
      "epoch": 0.00016332530317259402,
      "eval_loss": 1.775226354598999,
      "eval_runtime": 680.4665,
      "eval_samples_per_second": 3.789,
      "eval_steps_per_second": 1.894,
      "step": 1
    },
    {
      "epoch": 0.00032665060634518803,
      "grad_norm": 13.139348030090332,
      "learning_rate": 4e-05,
      "loss": 19.1948,
      "step": 2
    },
    {
      "epoch": 0.0004899759095177821,
      "grad_norm": 10.117087364196777,
      "learning_rate": 6e-05,
      "loss": 23.0937,
      "step": 3
    },
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 7.632481098175049,
      "learning_rate": 8e-05,
      "loss": 14.8729,
      "step": 4
    },
    {
      "epoch": 0.0008166265158629701,
      "grad_norm": 14.477787017822266,
      "learning_rate": 0.0001,
      "loss": 23.4074,
      "step": 5
    },
    {
      "epoch": 0.0008166265158629701,
      "eval_loss": 1.7739180326461792,
      "eval_runtime": 703.2361,
      "eval_samples_per_second": 3.666,
      "eval_steps_per_second": 1.833,
      "step": 5
    },
    {
      "epoch": 0.0009799518190355642,
      "grad_norm": 11.354787826538086,
      "learning_rate": 0.00012,
      "loss": 20.6137,
      "step": 6
    },
    {
      "epoch": 0.0011432771222081581,
      "grad_norm": 8.308173179626465,
      "learning_rate": 0.00014,
      "loss": 15.143,
      "step": 7
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 7.584307670593262,
      "learning_rate": 0.00016,
      "loss": 15.0567,
      "step": 8
    },
    {
      "epoch": 0.0014699277285533461,
      "grad_norm": 17.95978355407715,
      "learning_rate": 0.00018,
      "loss": 16.7341,
      "step": 9
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 9.063631057739258,
      "learning_rate": 0.0002,
      "loss": 12.5246,
      "step": 10
    },
    {
      "epoch": 0.0016332530317259401,
      "eval_loss": 1.8055723905563354,
      "eval_runtime": 691.4001,
      "eval_samples_per_second": 3.729,
      "eval_steps_per_second": 1.864,
      "step": 10
    },
    {
      "epoch": 0.001796578334898534,
      "grad_norm": 18.369661331176758,
      "learning_rate": 0.00019781476007338058,
      "loss": 16.7498,
      "step": 11
    },
    {
      "epoch": 0.0019599036380711283,
      "grad_norm": 141.58885192871094,
      "learning_rate": 0.0001913545457642601,
      "loss": 14.3132,
      "step": 12
    },
    {
      "epoch": 0.0021232289412437223,
      "grad_norm": 21.435638427734375,
      "learning_rate": 0.00018090169943749476,
      "loss": 17.8755,
      "step": 13
    },
    {
      "epoch": 0.0022865542444163163,
      "grad_norm": 32.77855682373047,
      "learning_rate": 0.00016691306063588583,
      "loss": 14.8908,
      "step": 14
    },
    {
      "epoch": 0.0024498795475889103,
      "grad_norm": 13.740817070007324,
      "learning_rate": 0.00015000000000000001,
      "loss": 12.916,
      "step": 15
    },
    {
      "epoch": 0.0024498795475889103,
      "eval_loss": 1.8550177812576294,
      "eval_runtime": 685.077,
      "eval_samples_per_second": 3.763,
      "eval_steps_per_second": 1.882,
      "step": 15
    },
    {
      "epoch": 0.0026132048507615043,
      "grad_norm": 17.10791778564453,
      "learning_rate": 0.00013090169943749476,
      "loss": 16.5775,
      "step": 16
    },
    {
      "epoch": 0.0027765301539340983,
      "grad_norm": 24.963502883911133,
      "learning_rate": 0.00011045284632676536,
      "loss": 11.7159,
      "step": 17
    },
    {
      "epoch": 0.0029398554571066922,
      "grad_norm": 15.869377136230469,
      "learning_rate": 8.954715367323468e-05,
      "loss": 13.8917,
      "step": 18
    },
    {
      "epoch": 0.0031031807602792862,
      "grad_norm": 71.64442443847656,
      "learning_rate": 6.909830056250527e-05,
      "loss": 16.4648,
      "step": 19
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 15.940417289733887,
      "learning_rate": 5.000000000000002e-05,
      "loss": 11.6998,
      "step": 20
    },
    {
      "epoch": 0.0032665060634518802,
      "eval_loss": 1.8210992813110352,
      "eval_runtime": 667.8863,
      "eval_samples_per_second": 3.86,
      "eval_steps_per_second": 1.93,
      "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2167222768238592.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}