{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.12793858947705103,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025587717895410203,
      "grad_norm": 8.334024429321289,
      "learning_rate": 5e-05,
      "loss": 2.6052,
      "step": 1
    },
    {
      "epoch": 0.0025587717895410203,
      "eval_loss": NaN,
      "eval_runtime": 74.5919,
      "eval_samples_per_second": 35.299,
      "eval_steps_per_second": 4.424,
      "step": 1
    },
    {
      "epoch": 0.005117543579082041,
      "grad_norm": 10.940125465393066,
      "learning_rate": 0.0001,
      "loss": 3.3579,
      "step": 2
    },
    {
      "epoch": 0.007676315368623061,
      "grad_norm": 7.787834167480469,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.181,
      "step": 3
    },
    {
      "epoch": 0.010235087158164081,
      "grad_norm": 7.5154948234558105,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.4313,
      "step": 4
    },
    {
      "epoch": 0.012793858947705102,
      "grad_norm": 8.15333080291748,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7125,
      "step": 5
    },
    {
      "epoch": 0.015352630737246123,
      "grad_norm": 6.947421073913574,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0752,
      "step": 6
    },
    {
      "epoch": 0.01791140252678714,
      "grad_norm": 4.807391166687012,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5733,
      "step": 7
    },
    {
      "epoch": 0.020470174316328162,
      "grad_norm": 8.114211082458496,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4164,
      "step": 8
    },
    {
      "epoch": 0.023028946105869183,
      "grad_norm": 3.900653123855591,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2119,
      "step": 9
    },
    {
      "epoch": 0.025587717895410204,
      "grad_norm": 4.901590824127197,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2332,
      "step": 10
    },
    {
      "epoch": 0.028146489684951224,
      "grad_norm": 2.4796481132507324,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1287,
      "step": 11
    },
    {
      "epoch": 0.030705261474492245,
      "grad_norm": 1.9578641653060913,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1035,
      "step": 12
    },
    {
      "epoch": 0.033264033264033266,
      "grad_norm": 3.6358413696289062,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3265,
      "step": 13
    },
    {
      "epoch": 0.03582280505357428,
      "grad_norm": 2.5038394927978516,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1806,
      "step": 14
    },
    {
      "epoch": 0.03838157684311531,
      "grad_norm": 1.8473141193389893,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.126,
      "step": 15
    },
    {
      "epoch": 0.040940348632656325,
      "grad_norm": 2.4110004901885986,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.1401,
      "step": 16
    },
    {
      "epoch": 0.04349912042219734,
      "grad_norm": 1.2881044149398804,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1238,
      "step": 17
    },
    {
      "epoch": 0.046057892211738366,
      "grad_norm": 1.0083253383636475,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.075,
      "step": 18
    },
    {
      "epoch": 0.04861666400127938,
      "grad_norm": 1.9869771003723145,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.07,
      "step": 19
    },
    {
      "epoch": 0.05117543579082041,
      "grad_norm": 1.36537766456604,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0881,
      "step": 20
    },
    {
      "epoch": 0.053734207580361425,
      "grad_norm": 1.1762269735336304,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0692,
      "step": 21
    },
    {
      "epoch": 0.05629297936990245,
      "grad_norm": 2.1188955307006836,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1169,
      "step": 22
    },
    {
      "epoch": 0.058851751159443466,
      "grad_norm": 1.6357115507125854,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0666,
      "step": 23
    },
    {
      "epoch": 0.06141052294898449,
      "grad_norm": 1.2706236839294434,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0406,
      "step": 24
    },
    {
      "epoch": 0.06396929473852551,
      "grad_norm": 2.2332940101623535,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0662,
      "step": 25
    },
    {
      "epoch": 0.06396929473852551,
      "eval_loss": NaN,
      "eval_runtime": 36.4427,
      "eval_samples_per_second": 72.25,
      "eval_steps_per_second": 9.055,
      "step": 25
    },
    {
      "epoch": 0.06652806652806653,
      "grad_norm": 1.6729117631912231,
      "learning_rate": 5e-05,
      "loss": 0.1896,
      "step": 26
    },
    {
      "epoch": 0.06908683831760755,
      "grad_norm": 0.7531017661094666,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0992,
      "step": 27
    },
    {
      "epoch": 0.07164561010714857,
      "grad_norm": 0.862877607345581,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0977,
      "step": 28
    },
    {
      "epoch": 0.07420438189668958,
      "grad_norm": 1.5235896110534668,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0702,
      "step": 29
    },
    {
      "epoch": 0.07676315368623061,
      "grad_norm": 1.0583374500274658,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.052,
      "step": 30
    },
    {
      "epoch": 0.07932192547577163,
      "grad_norm": 1.06094229221344,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0453,
      "step": 31
    },
    {
      "epoch": 0.08188069726531265,
      "grad_norm": 0.7197346687316895,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0613,
      "step": 32
    },
    {
      "epoch": 0.08443946905485367,
      "grad_norm": 1.0249391794204712,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0762,
      "step": 33
    },
    {
      "epoch": 0.08699824084439468,
      "grad_norm": 1.1629976034164429,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.102,
      "step": 34
    },
    {
      "epoch": 0.08955701263393571,
      "grad_norm": 0.8161555528640747,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0485,
      "step": 35
    },
    {
      "epoch": 0.09211578442347673,
      "grad_norm": 0.7493521571159363,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0812,
      "step": 36
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 1.0272088050842285,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0908,
      "step": 37
    },
    {
      "epoch": 0.09723332800255877,
      "grad_norm": 1.7803131341934204,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1749,
      "step": 38
    },
    {
      "epoch": 0.0997920997920998,
      "grad_norm": 1.0670037269592285,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0817,
      "step": 39
    },
    {
      "epoch": 0.10235087158164081,
      "grad_norm": 0.6444293260574341,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0544,
      "step": 40
    },
    {
      "epoch": 0.10490964337118183,
      "grad_norm": 0.5108956098556519,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0574,
      "step": 41
    },
    {
      "epoch": 0.10746841516072285,
      "grad_norm": 0.7616376876831055,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0522,
      "step": 42
    },
    {
      "epoch": 0.11002718695026387,
      "grad_norm": 0.6766124367713928,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0396,
      "step": 43
    },
    {
      "epoch": 0.1125859587398049,
      "grad_norm": 0.7287461757659912,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0636,
      "step": 44
    },
    {
      "epoch": 0.11514473052934592,
      "grad_norm": 1.3630841970443726,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0857,
      "step": 45
    },
    {
      "epoch": 0.11770350231888693,
      "grad_norm": 1.068311333656311,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.082,
      "step": 46
    },
    {
      "epoch": 0.12026227410842795,
      "grad_norm": 1.1175423860549927,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0288,
      "step": 47
    },
    {
      "epoch": 0.12282104589796898,
      "grad_norm": 0.9052390456199646,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0743,
      "step": 48
    },
    {
      "epoch": 0.12537981768751,
      "grad_norm": 0.9554215669631958,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0632,
      "step": 49
    },
    {
      "epoch": 0.12793858947705103,
      "grad_norm": 1.0501782894134521,
      "learning_rate": 0.0,
      "loss": 0.0551,
      "step": 50
    },
    {
      "epoch": 0.12793858947705103,
      "eval_loss": NaN,
      "eval_runtime": 72.5923,
      "eval_samples_per_second": 36.271,
      "eval_steps_per_second": 4.546,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.589463780163584e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}