{
  "best_metric": 0.757265567779541,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.017114495978093443,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006845798391237378,
      "grad_norm": 0.25282052159309387,
      "learning_rate": 0.0001,
      "loss": 0.5592,
      "step": 1
    },
    {
      "epoch": 0.0006845798391237378,
      "eval_loss": 0.9501175284385681,
      "eval_runtime": 173.9775,
      "eval_samples_per_second": 3.535,
      "eval_steps_per_second": 1.77,
      "step": 1
    },
    {
      "epoch": 0.0013691596782474755,
      "grad_norm": 0.5238334536552429,
      "learning_rate": 0.0002,
      "loss": 0.663,
      "step": 2
    },
    {
      "epoch": 0.0020537395173712133,
      "grad_norm": 0.5488997101783752,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.583,
      "step": 3
    },
    {
      "epoch": 0.002738319356494951,
      "grad_norm": 0.38578325510025024,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.6462,
      "step": 4
    },
    {
      "epoch": 0.003422899195618689,
      "grad_norm": 0.5969985723495483,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.737,
      "step": 5
    },
    {
      "epoch": 0.004107479034742427,
      "grad_norm": 0.677198588848114,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.721,
      "step": 6
    },
    {
      "epoch": 0.004792058873866164,
      "grad_norm": 0.43101000785827637,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.8587,
      "step": 7
    },
    {
      "epoch": 0.005476638712989902,
      "grad_norm": 0.43668434023857117,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.6926,
      "step": 8
    },
    {
      "epoch": 0.00616121855211364,
      "grad_norm": 0.4872725307941437,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.6979,
      "step": 9
    },
    {
      "epoch": 0.006845798391237378,
      "grad_norm": 0.45551222562789917,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.5902,
      "step": 10
    },
    {
      "epoch": 0.0075303782303611155,
      "grad_norm": 0.5328372716903687,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.8881,
      "step": 11
    },
    {
      "epoch": 0.008214958069484853,
      "grad_norm": 0.4792215824127197,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.7159,
      "step": 12
    },
    {
      "epoch": 0.008899537908608592,
      "grad_norm": 0.5611771941184998,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.7192,
      "step": 13
    },
    {
      "epoch": 0.009584117747732329,
      "grad_norm": 0.6743291020393372,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7356,
      "step": 14
    },
    {
      "epoch": 0.010268697586856067,
      "grad_norm": 0.6450310945510864,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.6947,
      "step": 15
    },
    {
      "epoch": 0.010953277425979804,
      "grad_norm": 0.6415031552314758,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.6267,
      "step": 16
    },
    {
      "epoch": 0.011637857265103543,
      "grad_norm": 0.6395275592803955,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.7378,
      "step": 17
    },
    {
      "epoch": 0.01232243710422728,
      "grad_norm": 0.6193127632141113,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7111,
      "step": 18
    },
    {
      "epoch": 0.013007016943351019,
      "grad_norm": 0.6310256123542786,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.7352,
      "step": 19
    },
    {
      "epoch": 0.013691596782474755,
      "grad_norm": 0.7274715304374695,
      "learning_rate": 0.000138268343236509,
      "loss": 0.7348,
      "step": 20
    },
    {
      "epoch": 0.014376176621598494,
      "grad_norm": 0.6225596070289612,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.8002,
      "step": 21
    },
    {
      "epoch": 0.015060756460722231,
      "grad_norm": 0.6990033388137817,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.7106,
      "step": 22
    },
    {
      "epoch": 0.01574533629984597,
      "grad_norm": 0.7687625288963318,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.7688,
      "step": 23
    },
    {
      "epoch": 0.016429916138969707,
      "grad_norm": 0.8566373586654663,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.9884,
      "step": 24
    },
    {
      "epoch": 0.017114495978093443,
      "grad_norm": 0.707819402217865,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.6778,
      "step": 25
    },
    {
      "epoch": 0.017114495978093443,
      "eval_loss": 0.757265567779541,
      "eval_runtime": 175.3735,
      "eval_samples_per_second": 3.507,
      "eval_steps_per_second": 1.756,
      "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": 3.70943641780224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}