{
  "best_metric": 0.34878861904144287,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06777363605557438,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013554727211114877,
      "grad_norm": 3.3763315677642822,
      "learning_rate": 5e-05,
      "loss": 2.1424,
      "step": 1
    },
    {
      "epoch": 0.0013554727211114877,
      "eval_loss": 2.15142822265625,
      "eval_runtime": 99.9108,
      "eval_samples_per_second": 49.744,
      "eval_steps_per_second": 6.226,
      "step": 1
    },
    {
      "epoch": 0.0027109454422229754,
      "grad_norm": 4.00703239440918,
      "learning_rate": 0.0001,
      "loss": 1.9617,
      "step": 2
    },
    {
      "epoch": 0.004066418163334463,
      "grad_norm": 4.4005446434021,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.9565,
      "step": 3
    },
    {
      "epoch": 0.005421890884445951,
      "grad_norm": 2.728137969970703,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2676,
      "step": 4
    },
    {
      "epoch": 0.006777363605557438,
      "grad_norm": 2.65754771232605,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9894,
      "step": 5
    },
    {
      "epoch": 0.008132836326668925,
      "grad_norm": 2.2339353561401367,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.8164,
      "step": 6
    },
    {
      "epoch": 0.009488309047780414,
      "grad_norm": 1.3696885108947754,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.609,
      "step": 7
    },
    {
      "epoch": 0.010843781768891902,
      "grad_norm": 1.4017082452774048,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5677,
      "step": 8
    },
    {
      "epoch": 0.012199254490003388,
      "grad_norm": 0.6293935775756836,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.1703,
      "step": 9
    },
    {
      "epoch": 0.013554727211114876,
      "grad_norm": 0.6255472302436829,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0563,
      "step": 10
    },
    {
      "epoch": 0.014910199932226365,
      "grad_norm": 0.46427881717681885,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0557,
      "step": 11
    },
    {
      "epoch": 0.01626567265333785,
      "grad_norm": 1.1536684036254883,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.3666,
      "step": 12
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 3.3044023513793945,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1331,
      "step": 13
    },
    {
      "epoch": 0.018976618095560827,
      "grad_norm": 1.8147028684616089,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7374,
      "step": 14
    },
    {
      "epoch": 0.020332090816672314,
      "grad_norm": 0.7124860286712646,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.587,
      "step": 15
    },
    {
      "epoch": 0.021687563537783804,
      "grad_norm": 0.8253095149993896,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5289,
      "step": 16
    },
    {
      "epoch": 0.02304303625889529,
      "grad_norm": 0.9700387120246887,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.588,
      "step": 17
    },
    {
      "epoch": 0.024398508980006776,
      "grad_norm": 0.7491101622581482,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5031,
      "step": 18
    },
    {
      "epoch": 0.025753981701118266,
      "grad_norm": 0.658585250377655,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.371,
      "step": 19
    },
    {
      "epoch": 0.027109454422229753,
      "grad_norm": 0.5979881286621094,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3764,
      "step": 20
    },
    {
      "epoch": 0.02846492714334124,
      "grad_norm": 0.3236429989337921,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1499,
      "step": 21
    },
    {
      "epoch": 0.02982039986445273,
      "grad_norm": 0.1420210599899292,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0144,
      "step": 22
    },
    {
      "epoch": 0.031175872585564215,
      "grad_norm": 0.09472154825925827,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0173,
      "step": 23
    },
    {
      "epoch": 0.0325313453066757,
      "grad_norm": 0.2316225916147232,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1172,
      "step": 24
    },
    {
      "epoch": 0.03388681802778719,
      "grad_norm": 0.8157581090927124,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3354,
      "step": 25
    },
    {
      "epoch": 0.03388681802778719,
      "eval_loss": 0.38506779074668884,
      "eval_runtime": 100.9968,
      "eval_samples_per_second": 49.209,
      "eval_steps_per_second": 6.159,
      "step": 25
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 1.72467839717865,
      "learning_rate": 5e-05,
      "loss": 0.8527,
      "step": 26
    },
    {
      "epoch": 0.03659776347001017,
      "grad_norm": 1.1683018207550049,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.5788,
      "step": 27
    },
    {
      "epoch": 0.037953236191121655,
      "grad_norm": 0.9099482297897339,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.5694,
      "step": 28
    },
    {
      "epoch": 0.03930870891223314,
      "grad_norm": 0.6733741164207458,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.4685,
      "step": 29
    },
    {
      "epoch": 0.04066418163334463,
      "grad_norm": 0.49673986434936523,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.4127,
      "step": 30
    },
    {
      "epoch": 0.042019654354456114,
      "grad_norm": 0.6410134434700012,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.4818,
      "step": 31
    },
    {
      "epoch": 0.04337512707556761,
      "grad_norm": 0.5478073358535767,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4067,
      "step": 32
    },
    {
      "epoch": 0.044730599796679094,
      "grad_norm": 0.5715470910072327,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.3379,
      "step": 33
    },
    {
      "epoch": 0.04608607251779058,
      "grad_norm": 0.12999820709228516,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0825,
      "step": 34
    },
    {
      "epoch": 0.047441545238902066,
      "grad_norm": 0.07671059668064117,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0155,
      "step": 35
    },
    {
      "epoch": 0.04879701796001355,
      "grad_norm": 0.041638992726802826,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.019,
      "step": 36
    },
    {
      "epoch": 0.05015249068112504,
      "grad_norm": 0.3261185884475708,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3185,
      "step": 37
    },
    {
      "epoch": 0.05150796340223653,
      "grad_norm": 0.9712899923324585,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6303,
      "step": 38
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 0.6599809527397156,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6388,
      "step": 39
    },
    {
      "epoch": 0.054218908844459505,
      "grad_norm": 0.6416831016540527,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.5922,
      "step": 40
    },
    {
      "epoch": 0.05557438156557099,
      "grad_norm": 0.5625379681587219,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.4985,
      "step": 41
    },
    {
      "epoch": 0.05692985428668248,
      "grad_norm": 0.5052372813224792,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4821,
      "step": 42
    },
    {
      "epoch": 0.058285327007793965,
      "grad_norm": 0.48581060767173767,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.4703,
      "step": 43
    },
    {
      "epoch": 0.05964079972890546,
      "grad_norm": 0.43107783794403076,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.381,
      "step": 44
    },
    {
      "epoch": 0.060996272450016945,
      "grad_norm": 0.43108266592025757,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.3847,
      "step": 45
    },
    {
      "epoch": 0.06235174517112843,
      "grad_norm": 0.34979385137557983,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.276,
      "step": 46
    },
    {
      "epoch": 0.06370721789223992,
      "grad_norm": 0.03745098039507866,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0183,
      "step": 47
    },
    {
      "epoch": 0.0650626906133514,
      "grad_norm": 0.03093818388879299,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0133,
      "step": 48
    },
    {
      "epoch": 0.06641816333446289,
      "grad_norm": 0.0694834515452385,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0597,
      "step": 49
    },
    {
      "epoch": 0.06777363605557438,
      "grad_norm": 0.46889737248420715,
      "learning_rate": 0.0,
      "loss": 0.3722,
      "step": 50
    },
    {
      "epoch": 0.06777363605557438,
      "eval_loss": 0.34878861904144287,
      "eval_runtime": 100.9258,
      "eval_samples_per_second": 49.244,
      "eval_steps_per_second": 6.163,
      "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": 2.3416719345608294e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}