{
  "best_metric": 3.7618730068206787,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12494143370295174,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002498828674059035,
      "grad_norm": 4.337242603302002,
      "learning_rate": 5e-05,
      "loss": 4.6981,
      "step": 1
    },
    {
      "epoch": 0.002498828674059035,
      "eval_loss": 6.5940022468566895,
      "eval_runtime": 182.4393,
      "eval_samples_per_second": 14.783,
      "eval_steps_per_second": 1.853,
      "step": 1
    },
    {
      "epoch": 0.00499765734811807,
      "grad_norm": 4.955698490142822,
      "learning_rate": 0.0001,
      "loss": 5.0599,
      "step": 2
    },
    {
      "epoch": 0.007496486022177105,
      "grad_norm": 4.462535858154297,
      "learning_rate": 9.989294616193017e-05,
      "loss": 5.0605,
      "step": 3
    },
    {
      "epoch": 0.00999531469623614,
      "grad_norm": 3.5575056076049805,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.9234,
      "step": 4
    },
    {
      "epoch": 0.012494143370295174,
      "grad_norm": 3.3950798511505127,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.45,
      "step": 5
    },
    {
      "epoch": 0.01499297204435421,
      "grad_norm": 3.7996106147766113,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.1886,
      "step": 6
    },
    {
      "epoch": 0.017491800718413244,
      "grad_norm": 3.800816297531128,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.1023,
      "step": 7
    },
    {
      "epoch": 0.01999062939247228,
      "grad_norm": 5.088438987731934,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.0358,
      "step": 8
    },
    {
      "epoch": 0.022489458066531312,
      "grad_norm": 4.0445237159729,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.9852,
      "step": 9
    },
    {
      "epoch": 0.024988286740590348,
      "grad_norm": 3.5826759338378906,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.9522,
      "step": 10
    },
    {
      "epoch": 0.027487115414649384,
      "grad_norm": 4.7892351150512695,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.2147,
      "step": 11
    },
    {
      "epoch": 0.02998594408870842,
      "grad_norm": 4.103363990783691,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.2712,
      "step": 12
    },
    {
      "epoch": 0.032484772762767455,
      "grad_norm": 4.026049613952637,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.9254,
      "step": 13
    },
    {
      "epoch": 0.03498360143682649,
      "grad_norm": 5.036865234375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.5679,
      "step": 14
    },
    {
      "epoch": 0.03748243011088552,
      "grad_norm": 4.105172157287598,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.4894,
      "step": 15
    },
    {
      "epoch": 0.03998125878494456,
      "grad_norm": 2.956922769546509,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.4566,
      "step": 16
    },
    {
      "epoch": 0.04248008745900359,
      "grad_norm": 2.8003828525543213,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.4771,
      "step": 17
    },
    {
      "epoch": 0.044978916133062624,
      "grad_norm": 2.8711392879486084,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.546,
      "step": 18
    },
    {
      "epoch": 0.04747774480712166,
      "grad_norm": 3.2936465740203857,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.386,
      "step": 19
    },
    {
      "epoch": 0.049976573481180696,
      "grad_norm": 3.357780694961548,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.6467,
      "step": 20
    },
    {
      "epoch": 0.05247540215523973,
      "grad_norm": 3.1653242111206055,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.6092,
      "step": 21
    },
    {
      "epoch": 0.05497423082929877,
      "grad_norm": 3.2049310207366943,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.682,
      "step": 22
    },
    {
      "epoch": 0.0574730595033578,
      "grad_norm": 2.8633809089660645,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.6819,
      "step": 23
    },
    {
      "epoch": 0.05997188817741684,
      "grad_norm": 2.999393939971924,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.927,
      "step": 24
    },
    {
      "epoch": 0.06247071685147587,
      "grad_norm": 3.604912281036377,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.1785,
      "step": 25
    },
    {
      "epoch": 0.06247071685147587,
      "eval_loss": 3.979649066925049,
      "eval_runtime": 182.4015,
      "eval_samples_per_second": 14.786,
      "eval_steps_per_second": 1.853,
      "step": 25
    },
    {
      "epoch": 0.06496954552553491,
      "grad_norm": 4.296840667724609,
      "learning_rate": 5e-05,
      "loss": 3.3863,
      "step": 26
    },
    {
      "epoch": 0.06746837419959394,
      "grad_norm": 3.490752935409546,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 3.4422,
      "step": 27
    },
    {
      "epoch": 0.06996720287365298,
      "grad_norm": 3.014132022857666,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.3839,
      "step": 28
    },
    {
      "epoch": 0.07246603154771201,
      "grad_norm": 2.7040884494781494,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.2062,
      "step": 29
    },
    {
      "epoch": 0.07496486022177104,
      "grad_norm": 2.5979323387145996,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.2445,
      "step": 30
    },
    {
      "epoch": 0.07746368889583008,
      "grad_norm": 2.275642156600952,
      "learning_rate": 3.392802673484193e-05,
      "loss": 3.3628,
      "step": 31
    },
    {
      "epoch": 0.07996251756988912,
      "grad_norm": 2.441134452819824,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.4309,
      "step": 32
    },
    {
      "epoch": 0.08246134624394814,
      "grad_norm": 2.5280280113220215,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 3.3952,
      "step": 33
    },
    {
      "epoch": 0.08496017491800718,
      "grad_norm": 2.8496410846710205,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.4203,
      "step": 34
    },
    {
      "epoch": 0.08745900359206622,
      "grad_norm": 2.837029218673706,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 3.6201,
      "step": 35
    },
    {
      "epoch": 0.08995783226612525,
      "grad_norm": 3.2579169273376465,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 3.6424,
      "step": 36
    },
    {
      "epoch": 0.09245666094018429,
      "grad_norm": 3.8555946350097656,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.9756,
      "step": 37
    },
    {
      "epoch": 0.09495548961424333,
      "grad_norm": 2.4215047359466553,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.5203,
      "step": 38
    },
    {
      "epoch": 0.09745431828830235,
      "grad_norm": 2.26440167427063,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.0814,
      "step": 39
    },
    {
      "epoch": 0.09995314696236139,
      "grad_norm": 2.147338628768921,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.1869,
      "step": 40
    },
    {
      "epoch": 0.10245197563642043,
      "grad_norm": 2.0386617183685303,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.1623,
      "step": 41
    },
    {
      "epoch": 0.10495080431047946,
      "grad_norm": 2.0972471237182617,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.2309,
      "step": 42
    },
    {
      "epoch": 0.1074496329845385,
      "grad_norm": 2.204071283340454,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.2569,
      "step": 43
    },
    {
      "epoch": 0.10994846165859753,
      "grad_norm": 2.1857094764709473,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.283,
      "step": 44
    },
    {
      "epoch": 0.11244729033265656,
      "grad_norm": 2.844620943069458,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.368,
      "step": 45
    },
    {
      "epoch": 0.1149461190067156,
      "grad_norm": 2.47475528717041,
      "learning_rate": 1.70370868554659e-06,
      "loss": 3.3236,
      "step": 46
    },
    {
      "epoch": 0.11744494768077464,
      "grad_norm": 2.659583330154419,
      "learning_rate": 9.607359798384785e-07,
      "loss": 3.5154,
      "step": 47
    },
    {
      "epoch": 0.11994377635483368,
      "grad_norm": 2.7696313858032227,
      "learning_rate": 4.277569313094809e-07,
      "loss": 3.7308,
      "step": 48
    },
    {
      "epoch": 0.1224426050288927,
      "grad_norm": 2.9520068168640137,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 3.6925,
      "step": 49
    },
    {
      "epoch": 0.12494143370295174,
      "grad_norm": 4.396042823791504,
      "learning_rate": 0.0,
      "loss": 4.3178,
      "step": 50
    },
    {
      "epoch": 0.12494143370295174,
      "eval_loss": 3.7618730068206787,
      "eval_runtime": 182.4574,
      "eval_samples_per_second": 14.782,
      "eval_steps_per_second": 1.852,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}