{
  "best_metric": 0.15517795085906982,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05914534969688008,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011829069939376016,
      "grad_norm": 0.635590672492981,
      "learning_rate": 5e-05,
      "loss": 0.2302,
      "step": 1
    },
    {
      "epoch": 0.0011829069939376016,
      "eval_loss": 0.47086963057518005,
      "eval_runtime": 255.2657,
      "eval_samples_per_second": 22.31,
      "eval_steps_per_second": 2.789,
      "step": 1
    },
    {
      "epoch": 0.002365813987875203,
      "grad_norm": 0.9065675139427185,
      "learning_rate": 0.0001,
      "loss": 0.2918,
      "step": 2
    },
    {
      "epoch": 0.003548720981812805,
      "grad_norm": 0.7614929676055908,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.2727,
      "step": 3
    },
    {
      "epoch": 0.004731627975750406,
      "grad_norm": 0.4675009250640869,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2082,
      "step": 4
    },
    {
      "epoch": 0.005914534969688009,
      "grad_norm": 0.482346773147583,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2287,
      "step": 5
    },
    {
      "epoch": 0.00709744196362561,
      "grad_norm": 0.42084217071533203,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2071,
      "step": 6
    },
    {
      "epoch": 0.008280348957563211,
      "grad_norm": 0.31585443019866943,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.2086,
      "step": 7
    },
    {
      "epoch": 0.009463255951500812,
      "grad_norm": 0.2503543496131897,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1735,
      "step": 8
    },
    {
      "epoch": 0.010646162945438416,
      "grad_norm": 0.27292177081108093,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2129,
      "step": 9
    },
    {
      "epoch": 0.011829069939376017,
      "grad_norm": 0.30195295810699463,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2245,
      "step": 10
    },
    {
      "epoch": 0.013011976933313619,
      "grad_norm": 0.2982107698917389,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1864,
      "step": 11
    },
    {
      "epoch": 0.01419488392725122,
      "grad_norm": 0.3648938834667206,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.2216,
      "step": 12
    },
    {
      "epoch": 0.015377790921188822,
      "grad_norm": 0.16153264045715332,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.143,
      "step": 13
    },
    {
      "epoch": 0.016560697915126422,
      "grad_norm": 0.15979722142219543,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.154,
      "step": 14
    },
    {
      "epoch": 0.017743604909064025,
      "grad_norm": 0.1585456281900406,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.1456,
      "step": 15
    },
    {
      "epoch": 0.018926511903001625,
      "grad_norm": 0.1791682243347168,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.1708,
      "step": 16
    },
    {
      "epoch": 0.020109418896939228,
      "grad_norm": 0.19297978281974792,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.169,
      "step": 17
    },
    {
      "epoch": 0.02129232589087683,
      "grad_norm": 0.19050578773021698,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1793,
      "step": 18
    },
    {
      "epoch": 0.02247523288481443,
      "grad_norm": 0.18916115164756775,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.1773,
      "step": 19
    },
    {
      "epoch": 0.023658139878752035,
      "grad_norm": 0.18883368372917175,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1649,
      "step": 20
    },
    {
      "epoch": 0.024841046872689634,
      "grad_norm": 0.19214721024036407,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1488,
      "step": 21
    },
    {
      "epoch": 0.026023953866627238,
      "grad_norm": 0.20093420147895813,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1561,
      "step": 22
    },
    {
      "epoch": 0.027206860860564838,
      "grad_norm": 0.22185377776622772,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1587,
      "step": 23
    },
    {
      "epoch": 0.02838976785450244,
      "grad_norm": 0.27509504556655884,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1918,
      "step": 24
    },
    {
      "epoch": 0.02957267484844004,
      "grad_norm": 0.3846838176250458,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.211,
      "step": 25
    },
    {
      "epoch": 0.02957267484844004,
      "eval_loss": 0.15904709696769714,
      "eval_runtime": 255.4028,
      "eval_samples_per_second": 22.298,
      "eval_steps_per_second": 2.788,
      "step": 25
    },
    {
      "epoch": 0.030755581842377644,
      "grad_norm": 0.11360311508178711,
      "learning_rate": 5e-05,
      "loss": 0.1298,
      "step": 26
    },
    {
      "epoch": 0.03193848883631525,
      "grad_norm": 0.13283145427703857,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.1454,
      "step": 27
    },
    {
      "epoch": 0.033121395830252844,
      "grad_norm": 0.13941703736782074,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.1489,
      "step": 28
    },
    {
      "epoch": 0.03430430282419045,
      "grad_norm": 0.15467329323291779,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1467,
      "step": 29
    },
    {
      "epoch": 0.03548720981812805,
      "grad_norm": 0.1567084640264511,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.1547,
      "step": 30
    },
    {
      "epoch": 0.03667011681206565,
      "grad_norm": 0.1724080890417099,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.1601,
      "step": 31
    },
    {
      "epoch": 0.03785302380600325,
      "grad_norm": 0.1829661726951599,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1651,
      "step": 32
    },
    {
      "epoch": 0.03903593079994085,
      "grad_norm": 0.16755975782871246,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.1355,
      "step": 33
    },
    {
      "epoch": 0.040218837793878456,
      "grad_norm": 0.22333097457885742,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1725,
      "step": 34
    },
    {
      "epoch": 0.04140174478781606,
      "grad_norm": 0.20624902844429016,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1475,
      "step": 35
    },
    {
      "epoch": 0.04258465178175366,
      "grad_norm": 0.2575368285179138,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1906,
      "step": 36
    },
    {
      "epoch": 0.04376755877569126,
      "grad_norm": 0.29051071405410767,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.1885,
      "step": 37
    },
    {
      "epoch": 0.04495046576962886,
      "grad_norm": 0.13400967419147491,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1131,
      "step": 38
    },
    {
      "epoch": 0.046133372763566466,
      "grad_norm": 0.12060488760471344,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.1296,
      "step": 39
    },
    {
      "epoch": 0.04731627975750407,
      "grad_norm": 0.13372822105884552,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1443,
      "step": 40
    },
    {
      "epoch": 0.048499186751441666,
      "grad_norm": 0.15063360333442688,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.1547,
      "step": 41
    },
    {
      "epoch": 0.04968209374537927,
      "grad_norm": 0.15621814131736755,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1441,
      "step": 42
    },
    {
      "epoch": 0.05086500073931687,
      "grad_norm": 0.15441331267356873,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.1262,
      "step": 43
    },
    {
      "epoch": 0.052047907733254475,
      "grad_norm": 0.17183248698711395,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1568,
      "step": 44
    },
    {
      "epoch": 0.05323081472719207,
      "grad_norm": 0.1854199767112732,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.1609,
      "step": 45
    },
    {
      "epoch": 0.054413721721129675,
      "grad_norm": 0.19609281420707703,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.159,
      "step": 46
    },
    {
      "epoch": 0.05559662871506728,
      "grad_norm": 0.2056037038564682,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.1503,
      "step": 47
    },
    {
      "epoch": 0.05677953570900488,
      "grad_norm": 0.21327050030231476,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.141,
      "step": 48
    },
    {
      "epoch": 0.05796244270294248,
      "grad_norm": 0.27148258686065674,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.1656,
      "step": 49
    },
    {
      "epoch": 0.05914534969688008,
      "grad_norm": 0.39363518357276917,
      "learning_rate": 0.0,
      "loss": 0.1781,
      "step": 50
    },
    {
      "epoch": 0.05914534969688008,
      "eval_loss": 0.15517795085906982,
      "eval_runtime": 255.3396,
      "eval_samples_per_second": 22.304,
      "eval_steps_per_second": 2.788,
      "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}