{
  "best_metric": 2.1861934661865234,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.017588989292702768,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035177978585405537,
      "grad_norm": 5.538167476654053,
      "learning_rate": 5e-05,
      "loss": 32.5311,
      "step": 1
    },
    {
      "epoch": 0.00035177978585405537,
      "eval_loss": 2.2996881008148193,
      "eval_runtime": 1602.8053,
      "eval_samples_per_second": 11.948,
      "eval_steps_per_second": 1.494,
      "step": 1
    },
    {
      "epoch": 0.0007035595717081107,
      "grad_norm": 7.6789164543151855,
      "learning_rate": 0.0001,
      "loss": 33.1713,
      "step": 2
    },
    {
      "epoch": 0.001055339357562166,
      "grad_norm": 7.3845014572143555,
      "learning_rate": 9.989294616193017e-05,
      "loss": 32.8712,
      "step": 3
    },
    {
      "epoch": 0.0014071191434162215,
      "grad_norm": 6.956945419311523,
      "learning_rate": 9.957224306869053e-05,
      "loss": 33.1673,
      "step": 4
    },
    {
      "epoch": 0.0017588989292702769,
      "grad_norm": 8.048707008361816,
      "learning_rate": 9.903926402016153e-05,
      "loss": 33.9079,
      "step": 5
    },
    {
      "epoch": 0.002110678715124332,
      "grad_norm": 9.416152000427246,
      "learning_rate": 9.829629131445342e-05,
      "loss": 33.522,
      "step": 6
    },
    {
      "epoch": 0.0024624585009783875,
      "grad_norm": 9.693207740783691,
      "learning_rate": 9.73465064747553e-05,
      "loss": 33.6303,
      "step": 7
    },
    {
      "epoch": 0.002814238286832443,
      "grad_norm": 9.254134178161621,
      "learning_rate": 9.619397662556435e-05,
      "loss": 34.7466,
      "step": 8
    },
    {
      "epoch": 0.0031660180726864984,
      "grad_norm": 14.359371185302734,
      "learning_rate": 9.484363707663442e-05,
      "loss": 36.0151,
      "step": 9
    },
    {
      "epoch": 0.0035177978585405538,
      "grad_norm": 15.26530933380127,
      "learning_rate": 9.330127018922194e-05,
      "loss": 36.3619,
      "step": 10
    },
    {
      "epoch": 0.0038695776443946088,
      "grad_norm": 17.525087356567383,
      "learning_rate": 9.157348061512727e-05,
      "loss": 38.7371,
      "step": 11
    },
    {
      "epoch": 0.004221357430248664,
      "grad_norm": 22.53554916381836,
      "learning_rate": 8.966766701456177e-05,
      "loss": 41.6351,
      "step": 12
    },
    {
      "epoch": 0.00457313721610272,
      "grad_norm": 22.92333221435547,
      "learning_rate": 8.759199037394887e-05,
      "loss": 39.7522,
      "step": 13
    },
    {
      "epoch": 0.004924917001956775,
      "grad_norm": 9.440299034118652,
      "learning_rate": 8.535533905932738e-05,
      "loss": 33.28,
      "step": 14
    },
    {
      "epoch": 0.0052766967878108305,
      "grad_norm": 10.076234817504883,
      "learning_rate": 8.296729075500344e-05,
      "loss": 33.4697,
      "step": 15
    },
    {
      "epoch": 0.005628476573664886,
      "grad_norm": 8.652132034301758,
      "learning_rate": 8.043807145043604e-05,
      "loss": 33.9816,
      "step": 16
    },
    {
      "epoch": 0.005980256359518941,
      "grad_norm": 8.856562614440918,
      "learning_rate": 7.777851165098012e-05,
      "loss": 34.08,
      "step": 17
    },
    {
      "epoch": 0.006332036145372997,
      "grad_norm": 9.761141777038574,
      "learning_rate": 7.500000000000001e-05,
      "loss": 32.3105,
      "step": 18
    },
    {
      "epoch": 0.006683815931227052,
      "grad_norm": 9.883894920349121,
      "learning_rate": 7.211443451095007e-05,
      "loss": 33.6084,
      "step": 19
    },
    {
      "epoch": 0.0070355957170811076,
      "grad_norm": 9.651225090026855,
      "learning_rate": 6.91341716182545e-05,
      "loss": 34.3374,
      "step": 20
    },
    {
      "epoch": 0.007387375502935163,
      "grad_norm": 10.468379974365234,
      "learning_rate": 6.607197326515808e-05,
      "loss": 34.8942,
      "step": 21
    },
    {
      "epoch": 0.0077391552887892175,
      "grad_norm": 11.01174259185791,
      "learning_rate": 6.294095225512603e-05,
      "loss": 35.4242,
      "step": 22
    },
    {
      "epoch": 0.008090935074643273,
      "grad_norm": 14.812124252319336,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 36.4068,
      "step": 23
    },
    {
      "epoch": 0.008442714860497328,
      "grad_norm": 14.898117065429688,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 38.8318,
      "step": 24
    },
    {
      "epoch": 0.008794494646351384,
      "grad_norm": 24.162452697753906,
      "learning_rate": 5.327015646150716e-05,
      "loss": 45.2215,
      "step": 25
    },
    {
      "epoch": 0.008794494646351384,
      "eval_loss": 2.192530632019043,
      "eval_runtime": 1599.3943,
      "eval_samples_per_second": 11.974,
      "eval_steps_per_second": 1.497,
      "step": 25
    },
    {
      "epoch": 0.00914627443220544,
      "grad_norm": 3.850252389907837,
      "learning_rate": 5e-05,
      "loss": 32.5252,
      "step": 26
    },
    {
      "epoch": 0.009498054218059495,
      "grad_norm": 3.9339077472686768,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 31.5305,
      "step": 27
    },
    {
      "epoch": 0.00984983400391355,
      "grad_norm": 4.544314384460449,
      "learning_rate": 4.347369038899744e-05,
      "loss": 32.7912,
      "step": 28
    },
    {
      "epoch": 0.010201613789767605,
      "grad_norm": 5.1566386222839355,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 33.4204,
      "step": 29
    },
    {
      "epoch": 0.010553393575621661,
      "grad_norm": 5.830033302307129,
      "learning_rate": 3.705904774487396e-05,
      "loss": 31.9166,
      "step": 30
    },
    {
      "epoch": 0.010905173361475716,
      "grad_norm": 7.928355693817139,
      "learning_rate": 3.392802673484193e-05,
      "loss": 32.5998,
      "step": 31
    },
    {
      "epoch": 0.011256953147329772,
      "grad_norm": 7.931662082672119,
      "learning_rate": 3.086582838174551e-05,
      "loss": 33.5552,
      "step": 32
    },
    {
      "epoch": 0.011608732933183827,
      "grad_norm": 8.679764747619629,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 35.0329,
      "step": 33
    },
    {
      "epoch": 0.011960512719037883,
      "grad_norm": 10.883329391479492,
      "learning_rate": 2.500000000000001e-05,
      "loss": 35.1929,
      "step": 34
    },
    {
      "epoch": 0.012312292504891938,
      "grad_norm": 11.988004684448242,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 36.985,
      "step": 35
    },
    {
      "epoch": 0.012664072290745993,
      "grad_norm": 14.921319961547852,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 38.2092,
      "step": 36
    },
    {
      "epoch": 0.013015852076600049,
      "grad_norm": 17.755186080932617,
      "learning_rate": 1.703270924499656e-05,
      "loss": 39.6091,
      "step": 37
    },
    {
      "epoch": 0.013367631862454104,
      "grad_norm": 22.678396224975586,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 39.4044,
      "step": 38
    },
    {
      "epoch": 0.01371941164830816,
      "grad_norm": 3.5891330242156982,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 33.0391,
      "step": 39
    },
    {
      "epoch": 0.014071191434162215,
      "grad_norm": 8.799407958984375,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 33.2429,
      "step": 40
    },
    {
      "epoch": 0.01442297122001627,
      "grad_norm": 4.962418556213379,
      "learning_rate": 8.426519384872733e-06,
      "loss": 33.156,
      "step": 41
    },
    {
      "epoch": 0.014774751005870326,
      "grad_norm": 5.748550891876221,
      "learning_rate": 6.698729810778065e-06,
      "loss": 31.7608,
      "step": 42
    },
    {
      "epoch": 0.015126530791724381,
      "grad_norm": 6.102511405944824,
      "learning_rate": 5.156362923365588e-06,
      "loss": 32.0973,
      "step": 43
    },
    {
      "epoch": 0.015478310577578435,
      "grad_norm": 6.81181526184082,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 34.2612,
      "step": 44
    },
    {
      "epoch": 0.01583009036343249,
      "grad_norm": 7.937811374664307,
      "learning_rate": 2.653493525244721e-06,
      "loss": 33.158,
      "step": 45
    },
    {
      "epoch": 0.016181870149286546,
      "grad_norm": 8.875764846801758,
      "learning_rate": 1.70370868554659e-06,
      "loss": 34.1222,
      "step": 46
    },
    {
      "epoch": 0.0165336499351406,
      "grad_norm": 10.221689224243164,
      "learning_rate": 9.607359798384785e-07,
      "loss": 35.9223,
      "step": 47
    },
    {
      "epoch": 0.016885429720994657,
      "grad_norm": 11.83366870880127,
      "learning_rate": 4.277569313094809e-07,
      "loss": 37.0314,
      "step": 48
    },
    {
      "epoch": 0.017237209506848712,
      "grad_norm": 14.52757740020752,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 38.5339,
      "step": 49
    },
    {
      "epoch": 0.017588989292702768,
      "grad_norm": 21.84239387512207,
      "learning_rate": 0.0,
      "loss": 45.6407,
      "step": 50
    },
    {
      "epoch": 0.017588989292702768,
      "eval_loss": 2.1861934661865234,
      "eval_runtime": 1604.544,
      "eval_samples_per_second": 11.935,
      "eval_steps_per_second": 1.492,
      "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": 5.658021338284032e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}