{
  "best_metric": 9.110738754272461,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.24760136180748993,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004952027236149799,
      "grad_norm": 12.20673656463623,
      "learning_rate": 5e-05,
      "loss": 11.9051,
      "step": 1
    },
    {
      "epoch": 0.004952027236149799,
      "eval_loss": 11.722996711730957,
      "eval_runtime": 6.1353,
      "eval_samples_per_second": 221.83,
      "eval_steps_per_second": 27.871,
      "step": 1
    },
    {
      "epoch": 0.009904054472299598,
      "grad_norm": 12.011367797851562,
      "learning_rate": 0.0001,
      "loss": 11.9104,
      "step": 2
    },
    {
      "epoch": 0.014856081708449397,
      "grad_norm": 11.740654945373535,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.799,
      "step": 3
    },
    {
      "epoch": 0.019808108944599195,
      "grad_norm": 10.475540161132812,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.5504,
      "step": 4
    },
    {
      "epoch": 0.024760136180748994,
      "grad_norm": 9.895306587219238,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.3337,
      "step": 5
    },
    {
      "epoch": 0.029712163416898793,
      "grad_norm": 9.671496391296387,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.1609,
      "step": 6
    },
    {
      "epoch": 0.03466419065304859,
      "grad_norm": 9.652698516845703,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.9602,
      "step": 7
    },
    {
      "epoch": 0.03961621788919839,
      "grad_norm": 9.689221382141113,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.7571,
      "step": 8
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 9.352873802185059,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.632,
      "step": 9
    },
    {
      "epoch": 0.04952027236149799,
      "grad_norm": 9.3535737991333,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.4693,
      "step": 10
    },
    {
      "epoch": 0.05447229959764779,
      "grad_norm": 8.54699420928955,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.2515,
      "step": 11
    },
    {
      "epoch": 0.059424326833797586,
      "grad_norm": 7.41646146774292,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.0133,
      "step": 12
    },
    {
      "epoch": 0.06437635406994738,
      "grad_norm": 6.901260852813721,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.1047,
      "step": 13
    },
    {
      "epoch": 0.06932838130609718,
      "grad_norm": 6.2330451011657715,
      "learning_rate": 8.535533905932738e-05,
      "loss": 9.9866,
      "step": 14
    },
    {
      "epoch": 0.07428040854224698,
      "grad_norm": 5.705456256866455,
      "learning_rate": 8.296729075500344e-05,
      "loss": 9.8955,
      "step": 15
    },
    {
      "epoch": 0.07923243577839678,
      "grad_norm": 5.269005298614502,
      "learning_rate": 8.043807145043604e-05,
      "loss": 9.825,
      "step": 16
    },
    {
      "epoch": 0.08418446301454657,
      "grad_norm": 4.895080089569092,
      "learning_rate": 7.777851165098012e-05,
      "loss": 9.7718,
      "step": 17
    },
    {
      "epoch": 0.08913649025069638,
      "grad_norm": 4.531023979187012,
      "learning_rate": 7.500000000000001e-05,
      "loss": 9.6751,
      "step": 18
    },
    {
      "epoch": 0.09408851748684617,
      "grad_norm": 4.077882289886475,
      "learning_rate": 7.211443451095007e-05,
      "loss": 9.6316,
      "step": 19
    },
    {
      "epoch": 0.09904054472299598,
      "grad_norm": 3.8790152072906494,
      "learning_rate": 6.91341716182545e-05,
      "loss": 9.5469,
      "step": 20
    },
    {
      "epoch": 0.10399257195914577,
      "grad_norm": 3.744359016418457,
      "learning_rate": 6.607197326515808e-05,
      "loss": 9.5268,
      "step": 21
    },
    {
      "epoch": 0.10894459919529557,
      "grad_norm": 3.7534265518188477,
      "learning_rate": 6.294095225512603e-05,
      "loss": 9.4586,
      "step": 22
    },
    {
      "epoch": 0.11389662643144537,
      "grad_norm": 3.547865629196167,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 9.3806,
      "step": 23
    },
    {
      "epoch": 0.11884865366759517,
      "grad_norm": 3.449463367462158,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 9.3509,
      "step": 24
    },
    {
      "epoch": 0.12380068090374496,
      "grad_norm": 3.9944748878479004,
      "learning_rate": 5.327015646150716e-05,
      "loss": 9.2734,
      "step": 25
    },
    {
      "epoch": 0.12380068090374496,
      "eval_loss": 9.319945335388184,
      "eval_runtime": 6.1325,
      "eval_samples_per_second": 221.934,
      "eval_steps_per_second": 27.884,
      "step": 25
    },
    {
      "epoch": 0.12875270813989476,
      "grad_norm": 3.141822338104248,
      "learning_rate": 5e-05,
      "loss": 9.3686,
      "step": 26
    },
    {
      "epoch": 0.13370473537604458,
      "grad_norm": 2.925520181655884,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 9.332,
      "step": 27
    },
    {
      "epoch": 0.13865676261219437,
      "grad_norm": 2.8429415225982666,
      "learning_rate": 4.347369038899744e-05,
      "loss": 9.3123,
      "step": 28
    },
    {
      "epoch": 0.14360878984834416,
      "grad_norm": 2.663667678833008,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 9.2803,
      "step": 29
    },
    {
      "epoch": 0.14856081708449395,
      "grad_norm": 2.525662899017334,
      "learning_rate": 3.705904774487396e-05,
      "loss": 9.2936,
      "step": 30
    },
    {
      "epoch": 0.15351284432064377,
      "grad_norm": 2.4328393936157227,
      "learning_rate": 3.392802673484193e-05,
      "loss": 9.2449,
      "step": 31
    },
    {
      "epoch": 0.15846487155679356,
      "grad_norm": 2.222417116165161,
      "learning_rate": 3.086582838174551e-05,
      "loss": 9.183,
      "step": 32
    },
    {
      "epoch": 0.16341689879294335,
      "grad_norm": 2.1309008598327637,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 9.1944,
      "step": 33
    },
    {
      "epoch": 0.16836892602909315,
      "grad_norm": 2.2700769901275635,
      "learning_rate": 2.500000000000001e-05,
      "loss": 9.1398,
      "step": 34
    },
    {
      "epoch": 0.17332095326524297,
      "grad_norm": 2.3253843784332275,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 9.1568,
      "step": 35
    },
    {
      "epoch": 0.17827298050139276,
      "grad_norm": 2.405583381652832,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 9.1506,
      "step": 36
    },
    {
      "epoch": 0.18322500773754255,
      "grad_norm": 2.8271777629852295,
      "learning_rate": 1.703270924499656e-05,
      "loss": 9.025,
      "step": 37
    },
    {
      "epoch": 0.18817703497369234,
      "grad_norm": 2.783236026763916,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 9.181,
      "step": 38
    },
    {
      "epoch": 0.19312906220984216,
      "grad_norm": 2.6467456817626953,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 9.1671,
      "step": 39
    },
    {
      "epoch": 0.19808108944599195,
      "grad_norm": 2.3731637001037598,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 9.1439,
      "step": 40
    },
    {
      "epoch": 0.20303311668214175,
      "grad_norm": 2.2230052947998047,
      "learning_rate": 8.426519384872733e-06,
      "loss": 9.1583,
      "step": 41
    },
    {
      "epoch": 0.20798514391829154,
      "grad_norm": 2.25925350189209,
      "learning_rate": 6.698729810778065e-06,
      "loss": 9.1528,
      "step": 42
    },
    {
      "epoch": 0.21293717115444136,
      "grad_norm": 2.134979724884033,
      "learning_rate": 5.156362923365588e-06,
      "loss": 9.1479,
      "step": 43
    },
    {
      "epoch": 0.21788919839059115,
      "grad_norm": 2.0616414546966553,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 9.1364,
      "step": 44
    },
    {
      "epoch": 0.22284122562674094,
      "grad_norm": 1.9881036281585693,
      "learning_rate": 2.653493525244721e-06,
      "loss": 9.0938,
      "step": 45
    },
    {
      "epoch": 0.22779325286289073,
      "grad_norm": 1.959113359451294,
      "learning_rate": 1.70370868554659e-06,
      "loss": 9.1185,
      "step": 46
    },
    {
      "epoch": 0.23274528009904055,
      "grad_norm": 2.01914381980896,
      "learning_rate": 9.607359798384785e-07,
      "loss": 9.1127,
      "step": 47
    },
    {
      "epoch": 0.23769730733519034,
      "grad_norm": 2.156982421875,
      "learning_rate": 4.277569313094809e-07,
      "loss": 9.0668,
      "step": 48
    },
    {
      "epoch": 0.24264933457134014,
      "grad_norm": 2.748440742492676,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 9.0733,
      "step": 49
    },
    {
      "epoch": 0.24760136180748993,
      "grad_norm": 3.4162144660949707,
      "learning_rate": 0.0,
      "loss": 9.0366,
      "step": 50
    },
    {
      "epoch": 0.24760136180748993,
      "eval_loss": 9.110738754272461,
      "eval_runtime": 6.161,
      "eval_samples_per_second": 220.907,
      "eval_steps_per_second": 27.755,
      "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": 232593832280064.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}