{
  "best_metric": 1.8252456188201904,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5934718100890207,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011869436201780416,
      "grad_norm": 0.6697233319282532,
      "learning_rate": 5e-05,
      "loss": 2.0943,
      "step": 1
    },
    {
      "epoch": 0.011869436201780416,
      "eval_loss": 2.16434907913208,
      "eval_runtime": 6.5003,
      "eval_samples_per_second": 87.381,
      "eval_steps_per_second": 10.923,
      "step": 1
    },
    {
      "epoch": 0.02373887240356083,
      "grad_norm": 0.7121739387512207,
      "learning_rate": 0.0001,
      "loss": 2.0255,
      "step": 2
    },
    {
      "epoch": 0.03560830860534125,
      "grad_norm": 0.6564896702766418,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.125,
      "step": 3
    },
    {
      "epoch": 0.04747774480712166,
      "grad_norm": 0.5123652219772339,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.0523,
      "step": 4
    },
    {
      "epoch": 0.05934718100890208,
      "grad_norm": 0.5332870483398438,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9956,
      "step": 5
    },
    {
      "epoch": 0.0712166172106825,
      "grad_norm": 0.5742672085762024,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.013,
      "step": 6
    },
    {
      "epoch": 0.0830860534124629,
      "grad_norm": 0.5574356317520142,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.9698,
      "step": 7
    },
    {
      "epoch": 0.09495548961424333,
      "grad_norm": 0.5041535496711731,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9257,
      "step": 8
    },
    {
      "epoch": 0.10682492581602374,
      "grad_norm": 0.47685691714286804,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9255,
      "step": 9
    },
    {
      "epoch": 0.11869436201780416,
      "grad_norm": 0.46352121233940125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9172,
      "step": 10
    },
    {
      "epoch": 0.13056379821958458,
      "grad_norm": 0.4706200659275055,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8964,
      "step": 11
    },
    {
      "epoch": 0.142433234421365,
      "grad_norm": 0.47910913825035095,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9102,
      "step": 12
    },
    {
      "epoch": 0.1543026706231454,
      "grad_norm": 0.5563710927963257,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.0062,
      "step": 13
    },
    {
      "epoch": 0.1661721068249258,
      "grad_norm": 0.6444411873817444,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8885,
      "step": 14
    },
    {
      "epoch": 0.17804154302670624,
      "grad_norm": 0.4616795778274536,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.9145,
      "step": 15
    },
    {
      "epoch": 0.18991097922848665,
      "grad_norm": 0.3399622142314911,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.8464,
      "step": 16
    },
    {
      "epoch": 0.20178041543026706,
      "grad_norm": 0.3937033414840698,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8395,
      "step": 17
    },
    {
      "epoch": 0.21364985163204747,
      "grad_norm": 0.4750767946243286,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9157,
      "step": 18
    },
    {
      "epoch": 0.22551928783382788,
      "grad_norm": 0.47759100794792175,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.8753,
      "step": 19
    },
    {
      "epoch": 0.23738872403560832,
      "grad_norm": 0.4606218636035919,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9086,
      "step": 20
    },
    {
      "epoch": 0.24925816023738873,
      "grad_norm": 0.4468643069267273,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.7881,
      "step": 21
    },
    {
      "epoch": 0.26112759643916916,
      "grad_norm": 0.46788281202316284,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8742,
      "step": 22
    },
    {
      "epoch": 0.27299703264094954,
      "grad_norm": 0.43544918298721313,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8698,
      "step": 23
    },
    {
      "epoch": 0.28486646884273,
      "grad_norm": 0.4608367085456848,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.8819,
      "step": 24
    },
    {
      "epoch": 0.29673590504451036,
      "grad_norm": 0.5243120789527893,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.9315,
      "step": 25
    },
    {
      "epoch": 0.29673590504451036,
      "eval_loss": 1.8553268909454346,
      "eval_runtime": 6.4943,
      "eval_samples_per_second": 87.461,
      "eval_steps_per_second": 10.933,
      "step": 25
    },
    {
      "epoch": 0.3086053412462908,
      "grad_norm": 0.6685218811035156,
      "learning_rate": 5e-05,
      "loss": 1.8927,
      "step": 26
    },
    {
      "epoch": 0.32047477744807124,
      "grad_norm": 0.6507945656776428,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.8866,
      "step": 27
    },
    {
      "epoch": 0.3323442136498516,
      "grad_norm": 0.637917697429657,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.8561,
      "step": 28
    },
    {
      "epoch": 0.34421364985163205,
      "grad_norm": 0.5948305130004883,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.7897,
      "step": 29
    },
    {
      "epoch": 0.3560830860534125,
      "grad_norm": 0.49185270071029663,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8109,
      "step": 30
    },
    {
      "epoch": 0.36795252225519287,
      "grad_norm": 0.43624943494796753,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.8639,
      "step": 31
    },
    {
      "epoch": 0.3798219584569733,
      "grad_norm": 0.38713496923446655,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8508,
      "step": 32
    },
    {
      "epoch": 0.3916913946587537,
      "grad_norm": 0.38741055130958557,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.8357,
      "step": 33
    },
    {
      "epoch": 0.4035608308605341,
      "grad_norm": 0.40148451924324036,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7832,
      "step": 34
    },
    {
      "epoch": 0.41543026706231456,
      "grad_norm": 0.4694264531135559,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.8257,
      "step": 35
    },
    {
      "epoch": 0.42729970326409494,
      "grad_norm": 0.49596676230430603,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.8726,
      "step": 36
    },
    {
      "epoch": 0.4391691394658754,
      "grad_norm": 0.6188309192657471,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.826,
      "step": 37
    },
    {
      "epoch": 0.45103857566765576,
      "grad_norm": 0.3719251751899719,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8437,
      "step": 38
    },
    {
      "epoch": 0.4629080118694362,
      "grad_norm": 0.3250787556171417,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.8298,
      "step": 39
    },
    {
      "epoch": 0.47477744807121663,
      "grad_norm": 0.3276398181915283,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.7952,
      "step": 40
    },
    {
      "epoch": 0.486646884272997,
      "grad_norm": 0.33880218863487244,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.7894,
      "step": 41
    },
    {
      "epoch": 0.49851632047477745,
      "grad_norm": 0.3426777720451355,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8094,
      "step": 42
    },
    {
      "epoch": 0.5103857566765578,
      "grad_norm": 0.3449629843235016,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.8138,
      "step": 43
    },
    {
      "epoch": 0.5222551928783383,
      "grad_norm": 0.3571850061416626,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7878,
      "step": 44
    },
    {
      "epoch": 0.5341246290801187,
      "grad_norm": 0.38788995146751404,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.7721,
      "step": 45
    },
    {
      "epoch": 0.5459940652818991,
      "grad_norm": 0.3872774541378021,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.7995,
      "step": 46
    },
    {
      "epoch": 0.5578635014836796,
      "grad_norm": 0.42015138268470764,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.8377,
      "step": 47
    },
    {
      "epoch": 0.56973293768546,
      "grad_norm": 0.4835258424282074,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.8335,
      "step": 48
    },
    {
      "epoch": 0.5816023738872403,
      "grad_norm": 0.5363931059837341,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.8543,
      "step": 49
    },
    {
      "epoch": 0.5934718100890207,
      "grad_norm": 0.6558699011802673,
      "learning_rate": 0.0,
      "loss": 1.8785,
      "step": 50
    },
    {
      "epoch": 0.5934718100890207,
      "eval_loss": 1.8252456188201904,
      "eval_runtime": 6.4997,
      "eval_samples_per_second": 87.388,
      "eval_steps_per_second": 10.924,
      "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}