{
  "best_metric": 0.536442756652832,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7835455435847208,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 1.1132760047912598,
      "learning_rate": 5e-05,
      "loss": 1.0471,
      "step": 1
    },
    {
      "epoch": 0.015670910871694418,
      "eval_loss": 1.4053739309310913,
      "eval_runtime": 29.206,
      "eval_samples_per_second": 14.723,
      "eval_steps_per_second": 1.849,
      "step": 1
    },
    {
      "epoch": 0.031341821743388835,
      "grad_norm": 1.2705464363098145,
      "learning_rate": 0.0001,
      "loss": 1.1524,
      "step": 2
    },
    {
      "epoch": 0.04701273261508325,
      "grad_norm": 1.1156189441680908,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.1526,
      "step": 3
    },
    {
      "epoch": 0.06268364348677767,
      "grad_norm": 0.7395751476287842,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9773,
      "step": 4
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.6252644062042236,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.909,
      "step": 5
    },
    {
      "epoch": 0.0940254652301665,
      "grad_norm": 0.6730421781539917,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.8153,
      "step": 6
    },
    {
      "epoch": 0.10969637610186092,
      "grad_norm": 0.7331916689872742,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7284,
      "step": 7
    },
    {
      "epoch": 0.12536728697355534,
      "grad_norm": 0.7444530129432678,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.725,
      "step": 8
    },
    {
      "epoch": 0.14103819784524976,
      "grad_norm": 0.6793332099914551,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6435,
      "step": 9
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.5083324909210205,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6286,
      "step": 10
    },
    {
      "epoch": 0.17238001958863858,
      "grad_norm": 0.5082964897155762,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.6137,
      "step": 11
    },
    {
      "epoch": 0.188050930460333,
      "grad_norm": 0.549592137336731,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5689,
      "step": 12
    },
    {
      "epoch": 0.20372184133202742,
      "grad_norm": 0.44566959142684937,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6379,
      "step": 13
    },
    {
      "epoch": 0.21939275220372184,
      "grad_norm": 0.3357296884059906,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6159,
      "step": 14
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.30138105154037476,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6075,
      "step": 15
    },
    {
      "epoch": 0.2507345739471107,
      "grad_norm": 0.33906084299087524,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6357,
      "step": 16
    },
    {
      "epoch": 0.2664054848188051,
      "grad_norm": 0.3230951428413391,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5907,
      "step": 17
    },
    {
      "epoch": 0.2820763956904995,
      "grad_norm": 0.2829711139202118,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6121,
      "step": 18
    },
    {
      "epoch": 0.29774730656219395,
      "grad_norm": 0.23465530574321747,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6035,
      "step": 19
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.24234157800674438,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5508,
      "step": 20
    },
    {
      "epoch": 0.32908912830558273,
      "grad_norm": 0.28421515226364136,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.5737,
      "step": 21
    },
    {
      "epoch": 0.34476003917727716,
      "grad_norm": 0.29918456077575684,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5379,
      "step": 22
    },
    {
      "epoch": 0.3604309500489716,
      "grad_norm": 0.2938958704471588,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5447,
      "step": 23
    },
    {
      "epoch": 0.376101860920666,
      "grad_norm": 0.3565478026866913,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.53,
      "step": 24
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.3841232657432556,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4817,
      "step": 25
    },
    {
      "epoch": 0.3917727717923604,
      "eval_loss": 0.5535266995429993,
      "eval_runtime": 29.1995,
      "eval_samples_per_second": 14.726,
      "eval_steps_per_second": 1.849,
      "step": 25
    },
    {
      "epoch": 0.40744368266405484,
      "grad_norm": 0.23766404390335083,
      "learning_rate": 5e-05,
      "loss": 0.6234,
      "step": 26
    },
    {
      "epoch": 0.42311459353574926,
      "grad_norm": 0.23127883672714233,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.6038,
      "step": 27
    },
    {
      "epoch": 0.4387855044074437,
      "grad_norm": 0.22502242028713226,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.598,
      "step": 28
    },
    {
      "epoch": 0.4544564152791381,
      "grad_norm": 0.23507346212863922,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.5594,
      "step": 29
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.2247634381055832,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.5735,
      "step": 30
    },
    {
      "epoch": 0.48579823702252695,
      "grad_norm": 0.23326322436332703,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.5991,
      "step": 31
    },
    {
      "epoch": 0.5014691478942214,
      "grad_norm": 0.2359481155872345,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5303,
      "step": 32
    },
    {
      "epoch": 0.5171400587659157,
      "grad_norm": 0.25685980916023254,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.5433,
      "step": 33
    },
    {
      "epoch": 0.5328109696376102,
      "grad_norm": 0.2492547184228897,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5567,
      "step": 34
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.2647036910057068,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.551,
      "step": 35
    },
    {
      "epoch": 0.564152791380999,
      "grad_norm": 0.26322075724601746,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.4919,
      "step": 36
    },
    {
      "epoch": 0.5798237022526934,
      "grad_norm": 0.28396323323249817,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.4601,
      "step": 37
    },
    {
      "epoch": 0.5954946131243879,
      "grad_norm": 0.2058783918619156,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5345,
      "step": 38
    },
    {
      "epoch": 0.6111655239960823,
      "grad_norm": 0.19112937152385712,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.5964,
      "step": 39
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.18986861407756805,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.5798,
      "step": 40
    },
    {
      "epoch": 0.6425073457394711,
      "grad_norm": 0.1978798359632492,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5386,
      "step": 41
    },
    {
      "epoch": 0.6581782566111655,
      "grad_norm": 0.19694554805755615,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5607,
      "step": 42
    },
    {
      "epoch": 0.67384916748286,
      "grad_norm": 0.21728673577308655,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.5868,
      "step": 43
    },
    {
      "epoch": 0.6895200783545543,
      "grad_norm": 0.19268789887428284,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5241,
      "step": 44
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.22148820757865906,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.551,
      "step": 45
    },
    {
      "epoch": 0.7208619000979432,
      "grad_norm": 0.21198055148124695,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.4969,
      "step": 46
    },
    {
      "epoch": 0.7365328109696376,
      "grad_norm": 0.2188008427619934,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.5173,
      "step": 47
    },
    {
      "epoch": 0.752203721841332,
      "grad_norm": 0.2279113531112671,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.4843,
      "step": 48
    },
    {
      "epoch": 0.7678746327130265,
      "grad_norm": 0.25976061820983887,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.4682,
      "step": 49
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.33424636721611023,
      "learning_rate": 0.0,
      "loss": 0.4384,
      "step": 50
    },
    {
      "epoch": 0.7835455435847208,
      "eval_loss": 0.536442756652832,
      "eval_runtime": 29.191,
      "eval_samples_per_second": 14.731,
      "eval_steps_per_second": 1.85,
      "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
}