{
  "best_metric": 0.7186086177825928,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5475701574264202,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.5382109880447388,
      "learning_rate": 5e-05,
      "loss": 0.6334,
      "step": 1
    },
    {
      "epoch": 0.010951403148528405,
      "eval_loss": 0.9221270680427551,
      "eval_runtime": 4.3892,
      "eval_samples_per_second": 140.117,
      "eval_steps_per_second": 17.543,
      "step": 1
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.7106021642684937,
      "learning_rate": 0.0001,
      "loss": 0.7209,
      "step": 2
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.6140474677085876,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.7701,
      "step": 3
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 0.5362752676010132,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7607,
      "step": 4
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.6057949662208557,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.7572,
      "step": 5
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.5503792762756348,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7435,
      "step": 6
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 0.43353062868118286,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7951,
      "step": 7
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 0.542281985282898,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8206,
      "step": 8
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.5608111023902893,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.8045,
      "step": 9
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 0.6318982243537903,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8273,
      "step": 10
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 0.6462970972061157,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.7675,
      "step": 11
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.6979478597640991,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.7839,
      "step": 12
    },
    {
      "epoch": 0.14236824093086928,
      "grad_norm": 0.36119213700294495,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6486,
      "step": 13
    },
    {
      "epoch": 0.15331964407939766,
      "grad_norm": 0.39019861817359924,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7194,
      "step": 14
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.3922410011291504,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.724,
      "step": 15
    },
    {
      "epoch": 0.17522245037645448,
      "grad_norm": 0.37384143471717834,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.7283,
      "step": 16
    },
    {
      "epoch": 0.1861738535249829,
      "grad_norm": 0.3727809190750122,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.721,
      "step": 17
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.3631754517555237,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8068,
      "step": 18
    },
    {
      "epoch": 0.2080766598220397,
      "grad_norm": 0.39393025636672974,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.726,
      "step": 19
    },
    {
      "epoch": 0.2190280629705681,
      "grad_norm": 0.419310986995697,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7185,
      "step": 20
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 0.4442942142486572,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7468,
      "step": 21
    },
    {
      "epoch": 0.24093086926762491,
      "grad_norm": 0.5004468560218811,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.7698,
      "step": 22
    },
    {
      "epoch": 0.2518822724161533,
      "grad_norm": 0.5305476784706116,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7442,
      "step": 23
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 0.6213279366493225,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.7515,
      "step": 24
    },
    {
      "epoch": 0.2737850787132101,
      "grad_norm": 0.8649816513061523,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.717,
      "step": 25
    },
    {
      "epoch": 0.2737850787132101,
      "eval_loss": 0.7244551777839661,
      "eval_runtime": 4.3949,
      "eval_samples_per_second": 139.934,
      "eval_steps_per_second": 17.52,
      "step": 25
    },
    {
      "epoch": 0.28473648186173856,
      "grad_norm": 0.23188556730747223,
      "learning_rate": 5e-05,
      "loss": 0.6339,
      "step": 26
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.3052370250225067,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.7263,
      "step": 27
    },
    {
      "epoch": 0.3066392881587953,
      "grad_norm": 0.32998526096343994,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.6687,
      "step": 28
    },
    {
      "epoch": 0.31759069130732376,
      "grad_norm": 0.3732319176197052,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6641,
      "step": 29
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.39839038252830505,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7225,
      "step": 30
    },
    {
      "epoch": 0.3394934976043806,
      "grad_norm": 0.43337464332580566,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7562,
      "step": 31
    },
    {
      "epoch": 0.35044490075290896,
      "grad_norm": 0.408007949590683,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7658,
      "step": 32
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.43947532773017883,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.7477,
      "step": 33
    },
    {
      "epoch": 0.3723477070499658,
      "grad_norm": 0.45250290632247925,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7523,
      "step": 34
    },
    {
      "epoch": 0.38329911019849416,
      "grad_norm": 0.4638631045818329,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.7515,
      "step": 35
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 0.5080087780952454,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.7318,
      "step": 36
    },
    {
      "epoch": 0.405201916495551,
      "grad_norm": 0.582893967628479,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.6909,
      "step": 37
    },
    {
      "epoch": 0.4161533196440794,
      "grad_norm": 0.22855021059513092,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5866,
      "step": 38
    },
    {
      "epoch": 0.4271047227926078,
      "grad_norm": 0.20767220854759216,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6823,
      "step": 39
    },
    {
      "epoch": 0.4380561259411362,
      "grad_norm": 0.23997880518436432,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.729,
      "step": 40
    },
    {
      "epoch": 0.4490075290896646,
      "grad_norm": 0.26613447070121765,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7155,
      "step": 41
    },
    {
      "epoch": 0.459958932238193,
      "grad_norm": 0.2961955666542053,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7087,
      "step": 42
    },
    {
      "epoch": 0.47091033538672145,
      "grad_norm": 0.31900477409362793,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7365,
      "step": 43
    },
    {
      "epoch": 0.48186173853524983,
      "grad_norm": 0.3380311131477356,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7116,
      "step": 44
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 0.3615745007991791,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.7719,
      "step": 45
    },
    {
      "epoch": 0.5037645448323066,
      "grad_norm": 0.4000967741012573,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7679,
      "step": 46
    },
    {
      "epoch": 0.5147159479808351,
      "grad_norm": 0.44231659173965454,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7702,
      "step": 47
    },
    {
      "epoch": 0.5256673511293635,
      "grad_norm": 0.48174336552619934,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.747,
      "step": 48
    },
    {
      "epoch": 0.5366187542778919,
      "grad_norm": 0.5735424160957336,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7402,
      "step": 49
    },
    {
      "epoch": 0.5475701574264202,
      "grad_norm": 0.6842880249023438,
      "learning_rate": 0.0,
      "loss": 0.703,
      "step": 50
    },
    {
      "epoch": 0.5475701574264202,
      "eval_loss": 0.7186086177825928,
      "eval_runtime": 4.3958,
      "eval_samples_per_second": 139.905,
      "eval_steps_per_second": 17.517,
      "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": 2.955777588540211e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}