{
  "best_metric": 0.9441007971763611,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7504690431519699,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0150093808630394,
      "grad_norm": 0.9536681771278381,
      "learning_rate": 5e-05,
      "loss": 1.2897,
      "step": 1
    },
    {
      "epoch": 0.0150093808630394,
      "eval_loss": 1.5068179368972778,
      "eval_runtime": 30.9392,
      "eval_samples_per_second": 14.512,
      "eval_steps_per_second": 1.842,
      "step": 1
    },
    {
      "epoch": 0.0300187617260788,
      "grad_norm": 1.0754947662353516,
      "learning_rate": 0.0001,
      "loss": 1.4698,
      "step": 2
    },
    {
      "epoch": 0.0450281425891182,
      "grad_norm": 0.9431746602058411,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.4191,
      "step": 3
    },
    {
      "epoch": 0.0600375234521576,
      "grad_norm": 0.5464565753936768,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2857,
      "step": 4
    },
    {
      "epoch": 0.075046904315197,
      "grad_norm": 0.6240769028663635,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.3134,
      "step": 5
    },
    {
      "epoch": 0.0900562851782364,
      "grad_norm": 0.7223731875419617,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.2049,
      "step": 6
    },
    {
      "epoch": 0.1050656660412758,
      "grad_norm": 0.6261888742446899,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1801,
      "step": 7
    },
    {
      "epoch": 0.1200750469043152,
      "grad_norm": 0.4351003170013428,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1348,
      "step": 8
    },
    {
      "epoch": 0.1350844277673546,
      "grad_norm": 0.3138794004917145,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.1162,
      "step": 9
    },
    {
      "epoch": 0.150093808630394,
      "grad_norm": 0.32999736070632935,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0348,
      "step": 10
    },
    {
      "epoch": 0.1651031894934334,
      "grad_norm": 0.3105546832084656,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0036,
      "step": 11
    },
    {
      "epoch": 0.1801125703564728,
      "grad_norm": 0.32986247539520264,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.9497,
      "step": 12
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.2528524398803711,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8764,
      "step": 13
    },
    {
      "epoch": 0.2101313320825516,
      "grad_norm": 0.27290859818458557,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9971,
      "step": 14
    },
    {
      "epoch": 0.225140712945591,
      "grad_norm": 0.2679688334465027,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.0029,
      "step": 15
    },
    {
      "epoch": 0.2401500938086304,
      "grad_norm": 0.258588969707489,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0006,
      "step": 16
    },
    {
      "epoch": 0.2551594746716698,
      "grad_norm": 0.25429263710975647,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.9921,
      "step": 17
    },
    {
      "epoch": 0.2701688555347092,
      "grad_norm": 0.22987525165081024,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9873,
      "step": 18
    },
    {
      "epoch": 0.2851782363977486,
      "grad_norm": 0.21064530313014984,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.0243,
      "step": 19
    },
    {
      "epoch": 0.300187617260788,
      "grad_norm": 0.19519351422786713,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0217,
      "step": 20
    },
    {
      "epoch": 0.3151969981238274,
      "grad_norm": 0.19835586845874786,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9752,
      "step": 21
    },
    {
      "epoch": 0.3302063789868668,
      "grad_norm": 0.20336930453777313,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.969,
      "step": 22
    },
    {
      "epoch": 0.3452157598499062,
      "grad_norm": 0.19671757519245148,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.9226,
      "step": 23
    },
    {
      "epoch": 0.3602251407129456,
      "grad_norm": 0.19592301547527313,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.9394,
      "step": 24
    },
    {
      "epoch": 0.37523452157598497,
      "grad_norm": 0.2190440446138382,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.8916,
      "step": 25
    },
    {
      "epoch": 0.37523452157598497,
      "eval_loss": 0.966587245464325,
      "eval_runtime": 30.8998,
      "eval_samples_per_second": 14.531,
      "eval_steps_per_second": 1.845,
      "step": 25
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.2631950378417969,
      "learning_rate": 5e-05,
      "loss": 0.881,
      "step": 26
    },
    {
      "epoch": 0.4052532833020638,
      "grad_norm": 0.2666192650794983,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.996,
      "step": 27
    },
    {
      "epoch": 0.4202626641651032,
      "grad_norm": 0.23546360433101654,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.008,
      "step": 28
    },
    {
      "epoch": 0.4352720450281426,
      "grad_norm": 0.20312005281448364,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9933,
      "step": 29
    },
    {
      "epoch": 0.450281425891182,
      "grad_norm": 0.1997581571340561,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.9833,
      "step": 30
    },
    {
      "epoch": 0.4652908067542214,
      "grad_norm": 0.20177055895328522,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.9664,
      "step": 31
    },
    {
      "epoch": 0.4803001876172608,
      "grad_norm": 0.215361088514328,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9785,
      "step": 32
    },
    {
      "epoch": 0.49530956848030017,
      "grad_norm": 0.23090364038944244,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.9036,
      "step": 33
    },
    {
      "epoch": 0.5103189493433395,
      "grad_norm": 0.21751844882965088,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9091,
      "step": 34
    },
    {
      "epoch": 0.525328330206379,
      "grad_norm": 0.22805064916610718,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.9488,
      "step": 35
    },
    {
      "epoch": 0.5403377110694184,
      "grad_norm": 0.21461419761180878,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8896,
      "step": 36
    },
    {
      "epoch": 0.5553470919324578,
      "grad_norm": 0.23005476593971252,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8975,
      "step": 37
    },
    {
      "epoch": 0.5703564727954972,
      "grad_norm": 0.17761656641960144,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8643,
      "step": 38
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.23044875264167786,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.942,
      "step": 39
    },
    {
      "epoch": 0.600375234521576,
      "grad_norm": 0.22395455837249756,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.0072,
      "step": 40
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.20301879942417145,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.9857,
      "step": 41
    },
    {
      "epoch": 0.6303939962476548,
      "grad_norm": 0.21255315840244293,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9321,
      "step": 42
    },
    {
      "epoch": 0.6454033771106942,
      "grad_norm": 0.19835422933101654,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.9564,
      "step": 43
    },
    {
      "epoch": 0.6604127579737336,
      "grad_norm": 0.18511104583740234,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9571,
      "step": 44
    },
    {
      "epoch": 0.6754221388367729,
      "grad_norm": 0.17117910087108612,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.9385,
      "step": 45
    },
    {
      "epoch": 0.6904315196998124,
      "grad_norm": 0.17859461903572083,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9538,
      "step": 46
    },
    {
      "epoch": 0.7054409005628518,
      "grad_norm": 0.18229509890079498,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.9689,
      "step": 47
    },
    {
      "epoch": 0.7204502814258912,
      "grad_norm": 0.17882877588272095,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8991,
      "step": 48
    },
    {
      "epoch": 0.7354596622889306,
      "grad_norm": 0.19296100735664368,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.877,
      "step": 49
    },
    {
      "epoch": 0.7504690431519699,
      "grad_norm": 0.2511255145072937,
      "learning_rate": 0.0,
      "loss": 0.8443,
      "step": 50
    },
    {
      "epoch": 0.7504690431519699,
      "eval_loss": 0.9441007971763611,
      "eval_runtime": 30.9402,
      "eval_samples_per_second": 14.512,
      "eval_steps_per_second": 1.842,
      "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": 5.968186696531968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}