{
  "best_metric": 0.20218083262443542,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0212630236019562,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008505209440782479,
      "grad_norm": 29.950550079345703,
      "learning_rate": 0.0001,
      "loss": 8.2158,
      "step": 1
    },
    {
      "epoch": 0.0008505209440782479,
      "eval_loss": 8.00285530090332,
      "eval_runtime": 36.2807,
      "eval_samples_per_second": 13.644,
      "eval_steps_per_second": 6.836,
      "step": 1
    },
    {
      "epoch": 0.0017010418881564958,
      "grad_norm": 30.36896324157715,
      "learning_rate": 0.0002,
      "loss": 7.8898,
      "step": 2
    },
    {
      "epoch": 0.0025515628322347436,
      "grad_norm": 23.313447952270508,
      "learning_rate": 0.00019978589232386035,
      "loss": 6.4148,
      "step": 3
    },
    {
      "epoch": 0.0034020837763129915,
      "grad_norm": 20.477699279785156,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.3799,
      "step": 4
    },
    {
      "epoch": 0.00425260472039124,
      "grad_norm": 15.300481796264648,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.4734,
      "step": 5
    },
    {
      "epoch": 0.005103125664469487,
      "grad_norm": 19.283344268798828,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.1708,
      "step": 6
    },
    {
      "epoch": 0.005953646608547736,
      "grad_norm": 13.99976634979248,
      "learning_rate": 0.0001946930129495106,
      "loss": 1.3736,
      "step": 7
    },
    {
      "epoch": 0.006804167552625983,
      "grad_norm": 4.875324249267578,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.2619,
      "step": 8
    },
    {
      "epoch": 0.007654688496704231,
      "grad_norm": 7.837060928344727,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.2082,
      "step": 9
    },
    {
      "epoch": 0.00850520944078248,
      "grad_norm": 18.53816032409668,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.2632,
      "step": 10
    },
    {
      "epoch": 0.009355730384860728,
      "grad_norm": 17.208162307739258,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.7963,
      "step": 11
    },
    {
      "epoch": 0.010206251328938975,
      "grad_norm": 7.137424945831299,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.4836,
      "step": 12
    },
    {
      "epoch": 0.011056772273017223,
      "grad_norm": 6.371276378631592,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.4192,
      "step": 13
    },
    {
      "epoch": 0.011907293217095471,
      "grad_norm": 5.845748424530029,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.1279,
      "step": 14
    },
    {
      "epoch": 0.01275781416117372,
      "grad_norm": 7.72625207901001,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.4695,
      "step": 15
    },
    {
      "epoch": 0.013608335105251966,
      "grad_norm": 3.310473918914795,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.1675,
      "step": 16
    },
    {
      "epoch": 0.014458856049330214,
      "grad_norm": 5.231335163116455,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.2699,
      "step": 17
    },
    {
      "epoch": 0.015309376993408463,
      "grad_norm": 4.628857612609863,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0697,
      "step": 18
    },
    {
      "epoch": 0.01615989793748671,
      "grad_norm": 5.772328853607178,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.2474,
      "step": 19
    },
    {
      "epoch": 0.01701041888156496,
      "grad_norm": 1.376090407371521,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0173,
      "step": 20
    },
    {
      "epoch": 0.017860939825643206,
      "grad_norm": 0.19068530201911926,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0022,
      "step": 21
    },
    {
      "epoch": 0.018711460769721456,
      "grad_norm": 3.4773025512695312,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.2143,
      "step": 22
    },
    {
      "epoch": 0.019561981713799702,
      "grad_norm": 3.134075403213501,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.1227,
      "step": 23
    },
    {
      "epoch": 0.02041250265787795,
      "grad_norm": 4.0494256019592285,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.183,
      "step": 24
    },
    {
      "epoch": 0.0212630236019562,
      "grad_norm": 3.598422050476074,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.1573,
      "step": 25
    },
    {
      "epoch": 0.0212630236019562,
      "eval_loss": 0.20218083262443542,
      "eval_runtime": 35.9031,
      "eval_samples_per_second": 13.787,
      "eval_steps_per_second": 6.907,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1802385752064000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}