{
  "best_metric": 2.467414617538452,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.62402496099844,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0124804992199688,
      "grad_norm": 87.66474914550781,
      "learning_rate": 5e-05,
      "loss": 43.1325,
      "step": 1
    },
    {
      "epoch": 0.0124804992199688,
      "eval_loss": 3.2597646713256836,
      "eval_runtime": 16.218,
      "eval_samples_per_second": 33.296,
      "eval_steps_per_second": 4.193,
      "step": 1
    },
    {
      "epoch": 0.0249609984399376,
      "grad_norm": 92.09264373779297,
      "learning_rate": 0.0001,
      "loss": 44.5978,
      "step": 2
    },
    {
      "epoch": 0.0374414976599064,
      "grad_norm": 40.381526947021484,
      "learning_rate": 9.989294616193017e-05,
      "loss": 44.7036,
      "step": 3
    },
    {
      "epoch": 0.0499219968798752,
      "grad_norm": 28.254507064819336,
      "learning_rate": 9.957224306869053e-05,
      "loss": 41.656,
      "step": 4
    },
    {
      "epoch": 0.062402496099843996,
      "grad_norm": 30.694181442260742,
      "learning_rate": 9.903926402016153e-05,
      "loss": 43.5891,
      "step": 5
    },
    {
      "epoch": 0.0748829953198128,
      "grad_norm": 48.97713851928711,
      "learning_rate": 9.829629131445342e-05,
      "loss": 43.8611,
      "step": 6
    },
    {
      "epoch": 0.0873634945397816,
      "grad_norm": 21.911754608154297,
      "learning_rate": 9.73465064747553e-05,
      "loss": 42.3794,
      "step": 7
    },
    {
      "epoch": 0.0998439937597504,
      "grad_norm": 27.891237258911133,
      "learning_rate": 9.619397662556435e-05,
      "loss": 43.527,
      "step": 8
    },
    {
      "epoch": 0.11232449297971919,
      "grad_norm": 26.46930503845215,
      "learning_rate": 9.484363707663442e-05,
      "loss": 44.036,
      "step": 9
    },
    {
      "epoch": 0.12480499219968799,
      "grad_norm": 26.584444046020508,
      "learning_rate": 9.330127018922194e-05,
      "loss": 44.037,
      "step": 10
    },
    {
      "epoch": 0.1372854914196568,
      "grad_norm": 31.118112564086914,
      "learning_rate": 9.157348061512727e-05,
      "loss": 43.5235,
      "step": 11
    },
    {
      "epoch": 0.1497659906396256,
      "grad_norm": 32.29335021972656,
      "learning_rate": 8.966766701456177e-05,
      "loss": 43.3974,
      "step": 12
    },
    {
      "epoch": 0.1622464898595944,
      "grad_norm": 29.30972671508789,
      "learning_rate": 8.759199037394887e-05,
      "loss": 41.2729,
      "step": 13
    },
    {
      "epoch": 0.1747269890795632,
      "grad_norm": 25.13165283203125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 40.0703,
      "step": 14
    },
    {
      "epoch": 0.187207488299532,
      "grad_norm": 17.516687393188477,
      "learning_rate": 8.296729075500344e-05,
      "loss": 39.6258,
      "step": 15
    },
    {
      "epoch": 0.1996879875195008,
      "grad_norm": 19.744029998779297,
      "learning_rate": 8.043807145043604e-05,
      "loss": 39.5522,
      "step": 16
    },
    {
      "epoch": 0.2121684867394696,
      "grad_norm": 22.51801109313965,
      "learning_rate": 7.777851165098012e-05,
      "loss": 42.303,
      "step": 17
    },
    {
      "epoch": 0.22464898595943839,
      "grad_norm": 17.72823143005371,
      "learning_rate": 7.500000000000001e-05,
      "loss": 40.2027,
      "step": 18
    },
    {
      "epoch": 0.23712948517940718,
      "grad_norm": 17.862627029418945,
      "learning_rate": 7.211443451095007e-05,
      "loss": 40.6478,
      "step": 19
    },
    {
      "epoch": 0.24960998439937598,
      "grad_norm": 18.495777130126953,
      "learning_rate": 6.91341716182545e-05,
      "loss": 40.8989,
      "step": 20
    },
    {
      "epoch": 0.2620904836193448,
      "grad_norm": 19.350662231445312,
      "learning_rate": 6.607197326515808e-05,
      "loss": 40.4955,
      "step": 21
    },
    {
      "epoch": 0.2745709828393136,
      "grad_norm": 26.270105361938477,
      "learning_rate": 6.294095225512603e-05,
      "loss": 40.6857,
      "step": 22
    },
    {
      "epoch": 0.2870514820592824,
      "grad_norm": 24.308195114135742,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 41.5772,
      "step": 23
    },
    {
      "epoch": 0.2995319812792512,
      "grad_norm": 27.439773559570312,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 43.7427,
      "step": 24
    },
    {
      "epoch": 0.31201248049922,
      "grad_norm": 36.69610595703125,
      "learning_rate": 5.327015646150716e-05,
      "loss": 46.5866,
      "step": 25
    },
    {
      "epoch": 0.31201248049922,
      "eval_loss": 2.520188093185425,
      "eval_runtime": 16.2098,
      "eval_samples_per_second": 33.313,
      "eval_steps_per_second": 4.195,
      "step": 25
    },
    {
      "epoch": 0.3244929797191888,
      "grad_norm": 13.912336349487305,
      "learning_rate": 5e-05,
      "loss": 38.242,
      "step": 26
    },
    {
      "epoch": 0.3369734789391576,
      "grad_norm": 15.16023063659668,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 37.8704,
      "step": 27
    },
    {
      "epoch": 0.3494539781591264,
      "grad_norm": 13.843705177307129,
      "learning_rate": 4.347369038899744e-05,
      "loss": 38.5292,
      "step": 28
    },
    {
      "epoch": 0.3619344773790952,
      "grad_norm": 14.417742729187012,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 40.0905,
      "step": 29
    },
    {
      "epoch": 0.374414976599064,
      "grad_norm": 16.50023651123047,
      "learning_rate": 3.705904774487396e-05,
      "loss": 39.7241,
      "step": 30
    },
    {
      "epoch": 0.3868954758190328,
      "grad_norm": 15.93111801147461,
      "learning_rate": 3.392802673484193e-05,
      "loss": 39.6588,
      "step": 31
    },
    {
      "epoch": 0.3993759750390016,
      "grad_norm": 17.797380447387695,
      "learning_rate": 3.086582838174551e-05,
      "loss": 39.841,
      "step": 32
    },
    {
      "epoch": 0.4118564742589704,
      "grad_norm": 20.05921745300293,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 40.0494,
      "step": 33
    },
    {
      "epoch": 0.4243369734789392,
      "grad_norm": 19.46441078186035,
      "learning_rate": 2.500000000000001e-05,
      "loss": 41.5063,
      "step": 34
    },
    {
      "epoch": 0.43681747269890797,
      "grad_norm": 21.7247314453125,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 41.4027,
      "step": 35
    },
    {
      "epoch": 0.44929797191887677,
      "grad_norm": 25.257909774780273,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 41.6081,
      "step": 36
    },
    {
      "epoch": 0.46177847113884557,
      "grad_norm": 29.84632682800293,
      "learning_rate": 1.703270924499656e-05,
      "loss": 41.5317,
      "step": 37
    },
    {
      "epoch": 0.47425897035881437,
      "grad_norm": 25.97105598449707,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 40.5494,
      "step": 38
    },
    {
      "epoch": 0.48673946957878317,
      "grad_norm": 11.205606460571289,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 37.0633,
      "step": 39
    },
    {
      "epoch": 0.49921996879875197,
      "grad_norm": 13.246723175048828,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 37.2773,
      "step": 40
    },
    {
      "epoch": 0.5117004680187207,
      "grad_norm": 16.231449127197266,
      "learning_rate": 8.426519384872733e-06,
      "loss": 38.797,
      "step": 41
    },
    {
      "epoch": 0.5241809672386896,
      "grad_norm": 16.365127563476562,
      "learning_rate": 6.698729810778065e-06,
      "loss": 39.0379,
      "step": 42
    },
    {
      "epoch": 0.5366614664586583,
      "grad_norm": 16.172225952148438,
      "learning_rate": 5.156362923365588e-06,
      "loss": 38.2024,
      "step": 43
    },
    {
      "epoch": 0.5491419656786272,
      "grad_norm": 16.4737548828125,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 39.3384,
      "step": 44
    },
    {
      "epoch": 0.5616224648985959,
      "grad_norm": 16.94817543029785,
      "learning_rate": 2.653493525244721e-06,
      "loss": 39.0274,
      "step": 45
    },
    {
      "epoch": 0.5741029641185648,
      "grad_norm": 20.8601131439209,
      "learning_rate": 1.70370868554659e-06,
      "loss": 41.5124,
      "step": 46
    },
    {
      "epoch": 0.5865834633385335,
      "grad_norm": 19.440319061279297,
      "learning_rate": 9.607359798384785e-07,
      "loss": 40.588,
      "step": 47
    },
    {
      "epoch": 0.5990639625585024,
      "grad_norm": 21.863067626953125,
      "learning_rate": 4.277569313094809e-07,
      "loss": 42.2265,
      "step": 48
    },
    {
      "epoch": 0.6115444617784711,
      "grad_norm": 25.434030532836914,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 43.0233,
      "step": 49
    },
    {
      "epoch": 0.62402496099844,
      "grad_norm": 37.389400482177734,
      "learning_rate": 0.0,
      "loss": 45.5068,
      "step": 50
    },
    {
      "epoch": 0.62402496099844,
      "eval_loss": 2.467414617538452,
      "eval_runtime": 16.6122,
      "eval_samples_per_second": 32.506,
      "eval_steps_per_second": 4.093,
      "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": 5.6633353939451904e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}